Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4429 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.3566. Min Act: -0.1700
Data Index: 5163989 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.3253. Min Act: -0.1700
Data Index: 483168 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.3253. Min Act: -0.1700
Data Index: 7582869 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.2941. Min Act: -0.1700
Data Index: 4280236 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.2628. Min Act: -0.1700
Data Index: 7233905 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.1378. Min Act: -0.1700
Data Index: 1999595 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.1066. Min Act: -0.1700
Data Index: 1435365 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0753. Min Act: -0.1700
Data Index: 7171818 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0753. Min Act: -0.1700
Data Index: 6412829 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0753. Min Act: -0.1700
Data Index: 2540574 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0753. Min Act: -0.1700
Data Index: 5205693 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0441. Min Act: -0.1700
Data Index: 774431 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0441. Min Act: -0.1700
Data Index: 7775823 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0128. Min Act: -0.1700
Data Index: 7714550 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4790349 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0128. Min Act: -0.1700
Data Index: 7691673 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4409950 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4012351 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3566. Min Range: -5.3566
Max Act: 5.0128. Min Act: -0.1700
Data Index: 8250622 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3566. Min Range: -5.3566
Max Act: 4.9816. Min Act: -0.1700
Data Index: 5137400 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19