Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5756 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2351. Min Range: -7.2351
Max Act: 7.2351. Min Act: -0.1700
Data Index: 786225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2351. Min Range: -7.2351
Max Act: 7.0476. Min Act: -0.1700
Data Index: 6007258 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.9851. Min Act: -0.1700
Data Index: 6712385 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.9539. Min Act: -0.1700
Data Index: 324686 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.9226. Min Act: -0.1700
Data Index: 3763221 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.9226. Min Act: -0.1700
Data Index: 5118161 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.8601. Min Act: -0.1700
Data Index: 262521 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.8289. Min Act: -0.1700
Data Index: 651448 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7664. Min Act: -0.1700
Data Index: 6158895 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7976. Min Act: -0.1700
Data Index: 936523 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7039. Min Act: -0.1700
Data Index: 3677987 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7351. Min Act: -0.1700
Data Index: 838787 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7039. Min Act: -0.1700
Data Index: 5828984 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7039. Min Act: -0.1700
Data Index: 1882452 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7039. Min Act: -0.1700
Data Index: 6013154 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7039. Min Act: -0.1700
Data Index: 4992165 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7039. Min Act: -0.1700
Data Index: 8335623 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.7039. Min Act: -0.1700
Data Index: 6949204 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.6726. Min Act: -0.1700
Data Index: 7008789 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2351. Min Range: -7.2351
Max Act: 6.6726. Min Act: -0.1700
Data Index: 7514120 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19