Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2245 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0326. Min Range: -7.0326
Max Act: 7.0326. Min Act: -0.1700
Data Index: 7537423 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0326. Min Range: -7.0326
Max Act: 7.0014. Min Act: -0.1700
Data Index: 2188632 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.8764. Min Act: -0.1700
Data Index: 5118668 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.8764. Min Act: -0.1700
Data Index: 2296056 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.7514. Min Act: -0.1700
Data Index: 5711394 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.6576. Min Act: -0.1700
Data Index: 1726465 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.5951. Min Act: -0.1700
Data Index: 186556 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.5951. Min Act: -0.1700
Data Index: 505988 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.5326. Min Act: -0.1700
Data Index: 8166057 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.5014. Min Act: -0.1700
Data Index: 8256852 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.4701. Min Act: -0.1700
Data Index: 6701399 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.4389. Min Act: -0.1700
Data Index: 4043842 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.4389. Min Act: -0.1700
Data Index: 5534710 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.4389. Min Act: -0.1700
Data Index: 4131563 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.4389. Min Act: -0.1700
Data Index: 1080888 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.4076. Min Act: -0.1700
Data Index: 4877617 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.4076. Min Act: -0.1700
Data Index: 5118669 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.3451. Min Act: -0.1700
Data Index: 1726463 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.3764. Min Act: -0.1700
Data Index: 8754744 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0326. Min Range: -7.0326
Max Act: 6.3764. Min Act: -0.1700
Data Index: 6260736 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19