Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5338 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0889. Min Range: -5.0889
Max Act: 5.0889. Min Act: -0.1700
Data Index: 719632 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0889. Min Range: -5.0889
Max Act: 5.0264. Min Act: -0.1700
Data Index: 6216573 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.9951. Min Act: -0.1700
Data Index: 655326 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.9639. Min Act: -0.1700
Data Index: 7567653 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.9326. Min Act: -0.1700
Data Index: 5962849 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.9639. Min Act: -0.1700
Data Index: 3714848 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.9951. Min Act: -0.1700
Data Index: 2204707 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.9326. Min Act: -0.1700
Data Index: 7743905 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.9326. Min Act: -0.1700
Data Index: 4432370 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.8389. Min Act: -0.1700
Data Index: 6660091 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.8076. Min Act: -0.1700
Data Index: 181636 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.8076. Min Act: -0.1700
Data Index: 5890174 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.8076. Min Act: -0.1700
Data Index: 4228898 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.7764. Min Act: -0.1700
Data Index: 5627268 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.7451. Min Act: -0.1700
Data Index: 1427747 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.7139. Min Act: -0.1700
Data Index: 4292601 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.7451. Min Act: -0.1700
Data Index: 6395412 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.7451. Min Act: -0.1700
Data Index: 8802392 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.6826. Min Act: -0.1700
Data Index: 4351302 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0889. Min Range: -5.0889
Max Act: 4.6826. Min Act: -0.1700
Data Index: 3385669 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19