Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 836 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1652. Min Range: -9.1652
Max Act: 9.1652. Min Act: -0.1700
Data Index: 4186422 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.8527. Min Act: -0.1700
Data Index: 2014551 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.5402. Min Act: -0.1700
Data Index: 3110240 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.4777. Min Act: -0.1700
Data Index: 80349 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.4777. Min Act: -0.1700
Data Index: 6035519 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.3527. Min Act: -0.1700
Data Index: 5378803 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.2277. Min Act: -0.1700
Data Index: 6032839 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.1652. Min Act: -0.1700
Data Index: 4907982 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.1652. Min Act: -0.1700
Data Index: 4110153 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.1652. Min Act: -0.1700
Data Index: 5989394 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.1652. Min Act: -0.1700
Data Index: 6470984 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.1652. Min Act: -0.1700
Data Index: 3256637 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.1652. Min Act: -0.1700
Data Index: 7943079 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.1027. Min Act: -0.1700
Data Index: 4018891 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.0714. Min Act: -0.1700
Data Index: 2932309 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.0402. Min Act: -0.1700
Data Index: 3170531 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.0714. Min Act: -0.1700
Data Index: 2191222 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.0714. Min Act: -0.1700
Data Index: 2528171 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1652. Min Range: -9.1652
Max Act: 8.0089. Min Act: -0.1700
Data Index: 1936592 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1652. Min Range: -9.1652
Max Act: 7.9777. Min Act: -0.1700
Data Index: 5161708 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19