Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.5615. Min Act: -0.1700
Data Index: 1407945 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4990. Min Act: -0.1700
Data Index: 6900736 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4990. Min Act: -0.1700
Data Index: 3259895 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4678. Min Act: -0.1700
Data Index: 6113776 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4365. Min Act: -0.1700
Data Index: 4520505 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4365. Min Act: -0.1700
Data Index: 3009132 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4053. Min Act: -0.1700
Data Index: 869803 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4053. Min Act: -0.1700
Data Index: 7252349 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3740. Min Act: -0.1700
Data Index: 17412 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3740. Min Act: -0.1700
Data Index: 4682737 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.4053. Min Act: -0.1700
Data Index: 3198545 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3740. Min Act: -0.1700
Data Index: 8771104 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3740. Min Act: -0.1700
Data Index: 3399072 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3428. Min Act: -0.1700
Data Index: 1525830 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3740. Min Act: -0.1700
Data Index: 8776896 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3428. Min Act: -0.1700
Data Index: 3147695 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3428. Min Act: -0.1700
Data Index: 4422844 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3428. Min Act: -0.1700
Data Index: 2337421 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3115. Min Act: -0.1700
Data Index: 1034849 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5615. Min Range: -4.5615
Max Act: 4.3115. Min Act: -0.1700
Data Index: 3193510 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19