Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.8757. Min Act: -0.1700
Data Index: 5454157 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.7507. Min Act: -0.1700
Data Index: 6606335 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.6882. Min Act: -0.1700
Data Index: 2630589 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.6882. Min Act: -0.1700
Data Index: 6606336 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.6882. Min Act: -0.1700
Data Index: 2878385 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.6569. Min Act: -0.1700
Data Index: 2930972 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5944. Min Act: -0.1700
Data Index: 6802370 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5944. Min Act: -0.1700
Data Index: 1099823 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5944. Min Act: -0.1700
Data Index: 7161494 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5944. Min Act: -0.1700
Data Index: 4606328 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.6257. Min Act: -0.1700
Data Index: 3796844 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5944. Min Act: -0.1700
Data Index: 6529415 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5944. Min Act: -0.1700
Data Index: 8559052 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5632. Min Act: -0.1700
Data Index: 7751690 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5632. Min Act: -0.1700
Data Index: 4328391 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5632. Min Act: -0.1700
Data Index: 5884393 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5007. Min Act: -0.1700
Data Index: 269164 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5632. Min Act: -0.1700
Data Index: 6156259 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5319. Min Act: -0.1700
Data Index: 5729708 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8757. Min Range: -5.8757
Max Act: 5.5319. Min Act: -0.1700
Data Index: 644453 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19