Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.5866. Min Act: -0.1700
Data Index: 3390576 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1392522 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.5241. Min Act: -0.1700
Data Index: 2034127 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.4303. Min Act: -0.1700
Data Index: 434170 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.4616. Min Act: -0.1700
Data Index: 4212259 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.4303. Min Act: -0.1700
Data Index: 5707016 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.3991. Min Act: -0.1700
Data Index: 2718537 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.3678. Min Act: -0.1700
Data Index: 4536617 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.3366. Min Act: -0.1700
Data Index: 2256948 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.3053. Min Act: -0.1700
Data Index: 6409840 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.2741. Min Act: -0.1700
Data Index: 7049651 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.2741. Min Act: -0.1700
Data Index: 3963460 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.2116. Min Act: -0.1700
Data Index: 8316050 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.1491. Min Act: -0.1700
Data Index: 3951949 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.1178. Min Act: -0.1700
Data Index: 2917922 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.1491. Min Act: -0.1700
Data Index: 4090643 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.1491. Min Act: -0.1700
Data Index: 3314883 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.1803. Min Act: -0.1700
Data Index: 1037730 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.0866. Min Act: -0.1700
Data Index: 6140800 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5866. Min Range: -5.5866
Max Act: 5.1178. Min Act: -0.1700
Data Index: 6649253 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19