Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3073. Min Range: -7.3073
Max Act: 7.3073. Min Act: -0.1700
Data Index: 7428564 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.8385. Min Act: -0.1700
Data Index: 6945574 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.7448. Min Act: -0.1700
Data Index: 50722 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.6823. Min Act: -0.1700
Data Index: 6344177 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.6823. Min Act: -0.1700
Data Index: 6111640 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.6198. Min Act: -0.1700
Data Index: 6854683 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.5885. Min Act: -0.1700
Data Index: 6634551 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.5573. Min Act: -0.1700
Data Index: 861326 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.5573. Min Act: -0.1700
Data Index: 1492213 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.5260. Min Act: -0.1700
Data Index: 778755 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.5260. Min Act: -0.1700
Data Index: 553530 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.4948. Min Act: -0.1700
Data Index: 7163388 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.4635. Min Act: -0.1700
Data Index: 4805089 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.4948. Min Act: -0.1700
Data Index: 6869139 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.4323. Min Act: -0.1700
Data Index: 6207759 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.4323. Min Act: -0.1700
Data Index: 5722238 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.4323. Min Act: -0.1700
Data Index: 5426587 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.4010. Min Act: -0.1700
Data Index: 6353853 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.3385. Min Act: -0.1700
Data Index: 7442602 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3073. Min Range: -7.3073
Max Act: 6.3698. Min Act: -0.1700
Data Index: 8552306 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19