Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1431 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1576. Min Range: -11.1576
Max Act: 11.1576. Min Act: -0.1700
Data Index: 6129719 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1576. Min Range: -11.1576
Max Act: 11.0951. Min Act: -0.1700
Data Index: 1554754 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1576. Min Range: -11.1576
Max Act: 11.0326. Min Act: -0.1700
Data Index: 5375865 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.8451. Min Act: -0.1700
Data Index: 4936919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.7201. Min Act: -0.1700
Data Index: 3835300 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.7826. Min Act: -0.1700
Data Index: 3359844 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.7201. Min Act: -0.1700
Data Index: 7339709 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.6576. Min Act: -0.1700
Data Index: 6438868 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.6576. Min Act: -0.1700
Data Index: 7835158 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.6576. Min Act: -0.1700
Data Index: 5657694 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.5951. Min Act: -0.1700
Data Index: 4046327 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.5951. Min Act: -0.1700
Data Index: 2726864 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.5951. Min Act: -0.1700
Data Index: 2819333 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.5951. Min Act: -0.1700
Data Index: 1407135 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.5326. Min Act: -0.1700
Data Index: 7610772 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.5326. Min Act: -0.1700
Data Index: 7888211 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.4701. Min Act: -0.1700
Data Index: 7337395 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.4701. Min Act: -0.1700
Data Index: 8208249 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.4076. Min Act: -0.1700
Data Index: 6621660 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1576. Min Range: -11.1576
Max Act: 10.4076. Min Act: -0.1700
Data Index: 1988813 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19