Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1161. Min Range: -6.1161
Max Act: 6.1161. Min Act: -0.1700
Data Index: 8216392 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.6786. Min Act: -0.1700
Data Index: 6231895 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.5849. Min Act: -0.1700
Data Index: 6017468 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.4911. Min Act: -0.1700
Data Index: 7870574 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.4911. Min Act: -0.1700
Data Index: 160791 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.5224. Min Act: -0.1700
Data Index: 3222749 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.4599. Min Act: -0.1700
Data Index: 6910973 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.4911. Min Act: -0.1700
Data Index: 2599775 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.4286. Min Act: -0.1700
Data Index: 2414748 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3974. Min Act: -0.1700
Data Index: 4570479 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3661. Min Act: -0.1700
Data Index: 8500266 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3661. Min Act: -0.1700
Data Index: 7327988 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3661. Min Act: -0.1700
Data Index: 5975843 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3661. Min Act: -0.1700
Data Index: 2412984 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3349. Min Act: -0.1700
Data Index: 1382836 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3349. Min Act: -0.1700
Data Index: 6253181 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3349. Min Act: -0.1700
Data Index: 6431150 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3349. Min Act: -0.1700
Data Index: 6972340 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3036. Min Act: -0.1700
Data Index: 7855252 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1161. Min Range: -6.1161
Max Act: 5.3036. Min Act: -0.1700
Data Index: 4064633 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19