Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.8480. Min Act: -0.1700
Data Index: 4485932 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.8480. Min Act: -0.1700
Data Index: 5215673 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.7855. Min Act: -0.1700
Data Index: 1126041 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.7542. Min Act: -0.1700
Data Index: 7195529 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.7542. Min Act: -0.1700
Data Index: 590347 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.7230. Min Act: -0.1700
Data Index: 3659472 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6917. Min Act: -0.1700
Data Index: 8117306 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6917. Min Act: -0.1700
Data Index: 6418864 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6605. Min Act: -0.1700
Data Index: 8614545 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6605. Min Act: -0.1700
Data Index: 4338644 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6605. Min Act: -0.1700
Data Index: 5074493 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6605. Min Act: -0.1700
Data Index: 1754729 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6605. Min Act: -0.1700
Data Index: 8358141 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.5980. Min Act: -0.1700
Data Index: 4349324 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.5980. Min Act: -0.1700
Data Index: 4433704 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6292. Min Act: -0.1700
Data Index: 5662854 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.6292. Min Act: -0.1700
Data Index: 2521164 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.5980. Min Act: -0.1700
Data Index: 35829 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.5980. Min Act: -0.1700
Data Index: 4485933 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8480. Min Range: -4.8480
Max Act: 4.5355. Min Act: -0.1700
Data Index: 1654016 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19