Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2847. Min Range: -11.2847
Max Act: 11.2847. Min Act: -0.1700
Data Index: 8147537 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2847. Min Range: -11.2847
Max Act: 11.0972. Min Act: -0.1700
Data Index: 7422522 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.9097. Min Act: -0.1700
Data Index: 5649561 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.9097. Min Act: -0.1700
Data Index: 5860378 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.8472. Min Act: -0.1700
Data Index: 2723584 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.8472. Min Act: -0.1700
Data Index: 1135053 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.7847. Min Act: -0.1700
Data Index: 5478192 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.7222. Min Act: -0.1700
Data Index: 4977702 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.7222. Min Act: -0.1700
Data Index: 8819808 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.6597. Min Act: -0.1700
Data Index: 7289861 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.6597. Min Act: -0.1700
Data Index: 5420312 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.6597. Min Act: -0.1700
Data Index: 7762107 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.7222. Min Act: -0.1700
Data Index: 526680 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.6597. Min Act: -0.1700
Data Index: 395811 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.6597. Min Act: -0.1700
Data Index: 7982866 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.5972. Min Act: -0.1700
Data Index: 6048038 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.5972. Min Act: -0.1700
Data Index: 8448992 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.5972. Min Act: -0.1700
Data Index: 7412797 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.6597. Min Act: -0.1700
Data Index: 2111508 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2847. Min Range: -11.2847
Max Act: 10.5972. Min Act: -0.1700
Data Index: 7831913 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19