Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.6480. Min Act: -0.1700
Data Index: 444035 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.6167. Min Act: -0.1700
Data Index: 8421863 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5855. Min Act: -0.1700
Data Index: 7008823 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5855. Min Act: -0.1700
Data Index: 8335042 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5855. Min Act: -0.1700
Data Index: 3777689 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5542. Min Act: -0.1700
Data Index: 2335542 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5230. Min Act: -0.1700
Data Index: 7902973 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5230. Min Act: -0.1700
Data Index: 453711 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5230. Min Act: -0.1700
Data Index: 2327209 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.5230. Min Act: -0.1700
Data Index: 5761155 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.4605. Min Act: -0.1700
Data Index: 1236528 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.4605. Min Act: -0.1700
Data Index: 4100269 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.4292. Min Act: -0.1700
Data Index: 444036 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.4292. Min Act: -0.1700
Data Index: 3621123 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.3979. Min Act: -0.1700
Data Index: 5243676 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.3979. Min Act: -0.1700
Data Index: 3967584 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.4292. Min Act: -0.1700
Data Index: 3451565 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.3979. Min Act: -0.1700
Data Index: 62660 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.3979. Min Act: -0.1700
Data Index: 7250297 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6480. Min Range: -4.6480
Max Act: 4.3667. Min Act: -0.1700
Data Index: 6975747 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19