Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.8334. Min Act: -0.1700
Data Index: 7325802 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.7084. Min Act: -0.1700
Data Index: 7325803 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.6459. Min Act: -0.1700
Data Index: 7325801 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.5834. Min Act: -0.1700
Data Index: 7325804 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.3959. Min Act: -0.1700
Data Index: 5725662 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.3334. Min Act: -0.1700
Data Index: 3832955 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.3334. Min Act: -0.1700
Data Index: 5762451 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.2084. Min Act: -0.1700
Data Index: 7702744 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.2084. Min Act: -0.1700
Data Index: 5725661 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.2084. Min Act: -0.1700
Data Index: 1442808 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.1459. Min Act: -0.1700
Data Index: 4520644 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.1459. Min Act: -0.1700
Data Index: 8549005 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.1459. Min Act: -0.1700
Data Index: 122032 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.1459. Min Act: -0.1700
Data Index: 4372769 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.0834. Min Act: -0.1700
Data Index: 2170923 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8334. Min Range: -9.8334
Max Act: 9.0209. Min Act: -0.1700
Data Index: 7130162 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8334. Min Range: -9.8334
Max Act: 8.9584. Min Act: -0.1700
Data Index: 3661779 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8334. Min Range: -9.8334
Max Act: 8.9584. Min Act: -0.1700
Data Index: 5226584 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8334. Min Range: -9.8334
Max Act: 8.8959. Min Act: -0.1700
Data Index: 3908153 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8334. Min Range: -9.8334
Max Act: 8.8334. Min Act: -0.1700
Data Index: 4125108 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19