Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6324 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1327. Min Range: -4.1327
Max Act: 4.1327. Min Act: -0.1700
Data Index: 5180197 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1327. Min Range: -4.1327
Max Act: 4.1327. Min Act: -0.1700
Data Index: 3546245 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1327. Min Range: -4.1327
Max Act: 4.0702. Min Act: -0.1700
Data Index: 6089362 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1327. Min Range: -4.1327
Max Act: 4.0076. Min Act: -0.1700
Data Index: 3728193 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9764. Min Act: -0.1700
Data Index: 6789050 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9764. Min Act: -0.1700
Data Index: 4668234 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9764. Min Act: -0.1700
Data Index: 7706 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9451. Min Act: -0.1700
Data Index: 2016368 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9451. Min Act: -0.1700
Data Index: 3044613 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9451. Min Act: -0.1700
Data Index: 2363765 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9139. Min Act: -0.1700
Data Index: 7025382 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9139. Min Act: -0.1700
Data Index: 663004 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9139. Min Act: -0.1700
Data Index: 1281326 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9451. Min Act: -0.1700
Data Index: 8691828 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9139. Min Act: -0.1700
Data Index: 4777419 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.9139. Min Act: -0.1700
Data Index: 8117582 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.8826. Min Act: -0.1700
Data Index: 1441747 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.8826. Min Act: -0.1700
Data Index: 903554 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.8826. Min Act: -0.1700
Data Index: 4575185 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1327. Min Range: -4.1327
Max Act: 3.8826. Min Act: -0.1700
Data Index: 2451306 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19