Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2112. Min Range: -7.2112
Max Act: 7.2112. Min Act: -0.1700
Data Index: 2873107 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2112. Min Range: -7.2112
Max Act: 7.1799. Min Act: -0.1700
Data Index: 4498787 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.8987. Min Act: -0.1700
Data Index: 4374119 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.8362. Min Act: -0.1700
Data Index: 7205273 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.8049. Min Act: -0.1700
Data Index: 8250556 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5862. Min Act: -0.1700
Data Index: 6179832 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5862. Min Act: -0.1700
Data Index: 4094611 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5549. Min Act: -0.1700
Data Index: 3473734 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5549. Min Act: -0.1700
Data Index: 7854326 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5549. Min Act: -0.1700
Data Index: 4234897 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5549. Min Act: -0.1700
Data Index: 6410681 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5862. Min Act: -0.1700
Data Index: 447146 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5237. Min Act: -0.1700
Data Index: 5886220 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5237. Min Act: -0.1700
Data Index: 4280443 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.5237. Min Act: -0.1700
Data Index: 8497930 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.4924. Min Act: -0.1700
Data Index: 3955545 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.4924. Min Act: -0.1700
Data Index: 2311754 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.4924. Min Act: -0.1700
Data Index: 2279509 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.4924. Min Act: -0.1700
Data Index: 2403043 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2112. Min Range: -7.2112
Max Act: 6.4299. Min Act: -0.1700
Data Index: 3815696 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19