Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.9466. Min Act: -0.1700
Data Index: 6915418 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.9466. Min Act: -0.1700
Data Index: 2068946 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.9153. Min Act: -0.1700
Data Index: 2904779 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8528. Min Act: -0.1700
Data Index: 595290 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8684. Min Act: -0.1700
Data Index: 1055411 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8372. Min Act: -0.1700
Data Index: 3608809 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8215. Min Act: -0.1700
Data Index: 1894954 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8215. Min Act: -0.1700
Data Index: 1617243 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8059. Min Act: -0.1700
Data Index: 5962883 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8215. Min Act: -0.1700
Data Index: 980460 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8059. Min Act: -0.1700
Data Index: 6839312 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8059. Min Act: -0.1700
Data Index: 1596275 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8059. Min Act: -0.1700
Data Index: 6886184 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.7903. Min Act: -0.1700
Data Index: 5462781 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.7903. Min Act: -0.1700
Data Index: 3818408 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8059. Min Act: -0.1700
Data Index: 5900931 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.7903. Min Act: -0.1700
Data Index: 117980 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.8059. Min Act: -0.1700
Data Index: 1602296 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.7903. Min Act: -0.1700
Data Index: 6971303 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9466. Min Range: -3.9466
Max Act: 3.7903. Min Act: -0.1700
Data Index: 7728283 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19