Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.9216. Min Act: -0.1700
Data Index: 6004282 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.9374. Min Act: -0.1700
Data Index: 6382890 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8899. Min Act: -0.1700
Data Index: 5485560 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.9058. Min Act: -0.1700
Data Index: 4327845 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8899. Min Act: -0.1700
Data Index: 7158454 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8423. Min Act: -0.1700
Data Index: 7607045 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8423. Min Act: -0.1700
Data Index: 5601708 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8104. Min Act: -0.1700
Data Index: 3521050 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8264. Min Act: -0.1700
Data Index: 113423 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8264. Min Act: -0.1700
Data Index: 7549895 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8423. Min Act: -0.1700
Data Index: 225245 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.8899. Min Act: -0.1700
Data Index: 4741364 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7945. Min Act: -0.1700
Data Index: 8286678 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7945. Min Act: -0.1700
Data Index: 2083968 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7945. Min Act: -0.1700
Data Index: 3454249 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7786. Min Act: -0.1700
Data Index: 7093422 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7626. Min Act: -0.1700
Data Index: 6083551 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7786. Min Act: -0.1700
Data Index: 1821053 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7626. Min Act: -0.1700
Data Index: 1920996 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9374. Min Range: -2.9374
Max Act: 2.7626. Min Act: -0.1700
Data Index: 6382891 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19