Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.3059. Min Range: -15.3059
Max Act: 15.3059. Min Act: -0.1700
Data Index: 4912592 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.3059. Min Range: -15.3059
Max Act: 15.1184. Min Act: -0.1700
Data Index: 8133012 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.9934. Min Act: -0.1700
Data Index: 7422498 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.8684. Min Act: -0.1700
Data Index: 4933807 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.9309. Min Act: -0.1700
Data Index: 8075393 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.8684. Min Act: -0.1700
Data Index: 3020825 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.7434. Min Act: -0.1700
Data Index: 154765 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.7434. Min Act: -0.1700
Data Index: 3470506 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.6809. Min Act: -0.1700
Data Index: 2920477 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.7434. Min Act: -0.1700
Data Index: 1739795 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.6809. Min Act: -0.1700
Data Index: 4528099 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.6809. Min Act: -0.1700
Data Index: 2449088 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.6809. Min Act: -0.1700
Data Index: 3045516 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.6184. Min Act: -0.1700
Data Index: 227474 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.5559. Min Act: -0.1700
Data Index: 6800726 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.5559. Min Act: -0.1700
Data Index: 4572908 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.4934. Min Act: -0.1700
Data Index: 3539983 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.4309. Min Act: -0.1700
Data Index: 2650669 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.4309. Min Act: -0.1700
Data Index: 6632202 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.3059. Min Range: -15.3059
Max Act: 14.3684. Min Act: -0.1700
Data Index: 1513300 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19