Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 861 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 315124 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8528. Min Act: -0.1700
Data Index: 915299 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8369. Min Act: -0.1700
Data Index: 1220980 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.7254. Min Act: -0.1700
Data Index: 1019190 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.7573. Min Act: -0.1700
Data Index: 5871648 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.7254. Min Act: -0.1700
Data Index: 6628935 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.7254. Min Act: -0.1700
Data Index: 6118408 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.7254. Min Act: -0.1700
Data Index: 1548603 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.7094. Min Act: -0.1700
Data Index: 7220477 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6774. Min Act: -0.1700
Data Index: 6198522 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6934. Min Act: -0.1700
Data Index: 3218365 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6774. Min Act: -0.1700
Data Index: 2857163 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6613. Min Act: -0.1700
Data Index: 1071685 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6613. Min Act: -0.1700
Data Index: 8537697 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6453. Min Act: -0.1700
Data Index: 7441878 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6292. Min Act: -0.1700
Data Index: 3614333 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6453. Min Act: -0.1700
Data Index: 8358598 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6453. Min Act: -0.1700
Data Index: 3698380 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6453. Min Act: -0.1700
Data Index: 4041391 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.6453. Min Act: -0.1700
Data Index: 362606 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19