Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.9210. Min Act: -0.1700
Data Index: 4426950 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.7960. Min Act: -0.1700
Data Index: 2347560 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.7335. Min Act: -0.1700
Data Index: 1837874 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.6398. Min Act: -0.1700
Data Index: 4917168 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.6398. Min Act: -0.1700
Data Index: 6328719 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.5773. Min Act: -0.1700
Data Index: 5299804 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.5773. Min Act: -0.1700
Data Index: 7650694 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4835. Min Act: -0.1700
Data Index: 1133014 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4835. Min Act: -0.1700
Data Index: 7916077 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.5148. Min Act: -0.1700
Data Index: 6612813 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4523. Min Act: -0.1700
Data Index: 7323958 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4523. Min Act: -0.1700
Data Index: 2994817 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4835. Min Act: -0.1700
Data Index: 5834907 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4835. Min Act: -0.1700
Data Index: 3857666 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4523. Min Act: -0.1700
Data Index: 6042588 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.4210. Min Act: -0.1700
Data Index: 5441265 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.3585. Min Act: -0.1700
Data Index: 712927 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.3898. Min Act: -0.1700
Data Index: 6963494 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.3273. Min Act: -0.1700
Data Index: 38503 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9210. Min Range: -6.9210
Max Act: 6.3585. Min Act: -0.1700
Data Index: 3825319 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19