Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1781 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.4228. Min Act: -0.1700
Data Index: 2214534 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.3603. Min Act: -0.1700
Data Index: 3253944 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.3290. Min Act: -0.1700
Data Index: 4985214 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2978. Min Act: -0.1700
Data Index: 2391084 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2353. Min Act: -0.1700
Data Index: 4659366 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2978. Min Act: -0.1700
Data Index: 520079 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2353. Min Act: -0.1700
Data Index: 5747762 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2040. Min Act: -0.1700
Data Index: 5761939 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2353. Min Act: -0.1700
Data Index: 3963648 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2040. Min Act: -0.1700
Data Index: 677732 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3779966 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1728. Min Act: -0.1700
Data Index: 2011274 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3345592 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.2040. Min Act: -0.1700
Data Index: 2394020 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1415. Min Act: -0.1700
Data Index: 5510428 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1415. Min Act: -0.1700
Data Index: 2574243 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1415. Min Act: -0.1700
Data Index: 603241 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1415. Min Act: -0.1700
Data Index: 261777 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1103. Min Act: -0.1700
Data Index: 613944 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4228. Min Range: -5.4228
Max Act: 5.1415. Min Act: -0.1700
Data Index: 1179408 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19