Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5256 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.8566. Min Act: -0.1700
Data Index: 8564101 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.7002. Min Act: -0.1700
Data Index: 4405080 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.6376. Min Act: -0.1700
Data Index: 892662 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.6376. Min Act: -0.1700
Data Index: 990455 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.6376. Min Act: -0.1700
Data Index: 4086765 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.6376. Min Act: -0.1700
Data Index: 4534042 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.6063. Min Act: -0.1700
Data Index: 628838 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5906. Min Act: -0.1700
Data Index: 2236688 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5906. Min Act: -0.1700
Data Index: 3229049 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.6063. Min Act: -0.1700
Data Index: 5557570 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5593. Min Act: -0.1700
Data Index: 1262493 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5593. Min Act: -0.1700
Data Index: 5773836 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5593. Min Act: -0.1700
Data Index: 8374354 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5593. Min Act: -0.1700
Data Index: 4562746 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5593. Min Act: -0.1700
Data Index: 7606443 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5437. Min Act: -0.1700
Data Index: 2937403 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5437. Min Act: -0.1700
Data Index: 3069030 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5280. Min Act: -0.1700
Data Index: 7169072 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5124. Min Act: -0.1700
Data Index: 8684035 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8566. Min Range: -3.8566
Max Act: 3.5124. Min Act: -0.1700
Data Index: 329521 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19