Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1324 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0355. Min Range: -4.0355
Max Act: 4.0355. Min Act: -0.1700
Data Index: 5665557 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0355. Min Range: -4.0355
Max Act: 4.0043. Min Act: -0.1700
Data Index: 5413109 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0355. Min Range: -4.0355
Max Act: 4.0355. Min Act: -0.1700
Data Index: 4395170 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0355. Min Range: -4.0355
Max Act: 4.0043. Min Act: -0.1700
Data Index: 4425708 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0355. Min Range: -4.0355
Max Act: 4.0043. Min Act: -0.1700
Data Index: 1121647 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9730. Min Act: -0.1700
Data Index: 3687255 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0355. Min Range: -4.0355
Max Act: 4.0043. Min Act: -0.1700
Data Index: 693023 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9730. Min Act: -0.1700
Data Index: 6082580 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9730. Min Act: -0.1700
Data Index: 4162602 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9417. Min Act: -0.1700
Data Index: 7618096 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9417. Min Act: -0.1700
Data Index: 1298579 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9730. Min Act: -0.1700
Data Index: 5406967 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9417. Min Act: -0.1700
Data Index: 4053365 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9105. Min Act: -0.1700
Data Index: 5435894 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9105. Min Act: -0.1700
Data Index: 8242230 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9105. Min Act: -0.1700
Data Index: 7561562 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9105. Min Act: -0.1700
Data Index: 5371291 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9105. Min Act: -0.1700
Data Index: 1040388 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.9105. Min Act: -0.1700
Data Index: 5639299 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0355. Min Range: -4.0355
Max Act: 3.8792. Min Act: -0.1700
Data Index: 1953285 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19