Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4192 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.8552. Min Act: -0.1700
Data Index: 1840269 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.7927. Min Act: -0.1700
Data Index: 4949016 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.6989. Min Act: -0.1700
Data Index: 6417469 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.6989. Min Act: -0.1700
Data Index: 4949018 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.6052. Min Act: -0.1700
Data Index: 4949017 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.5739. Min Act: -0.1700
Data Index: 8055515 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.4802. Min Act: -0.1700
Data Index: 4304622 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.4177. Min Act: -0.1700
Data Index: 4707386 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.3864. Min Act: -0.1700
Data Index: 937999 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.3552. Min Act: -0.1700
Data Index: 7295999 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.3552. Min Act: -0.1700
Data Index: 543451 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.3239. Min Act: -0.1700
Data Index: 1792968 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2927. Min Act: -0.1700
Data Index: 938000 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2614. Min Act: -0.1700
Data Index: 2468231 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2927. Min Act: -0.1700
Data Index: 4980221 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2614. Min Act: -0.1700
Data Index: 1888026 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2614. Min Act: -0.1700
Data Index: 7356146 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2302. Min Act: -0.1700
Data Index: 6960515 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2302. Min Act: -0.1700
Data Index: 2510750 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8552. Min Range: -6.8552
Max Act: 6.2302. Min Act: -0.1700
Data Index: 2725812 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19