Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.5374. Min Act: -0.1700
Data Index: 3398794 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.3186. Min Act: -0.1700
Data Index: 5627819 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.2874. Min Act: -0.1700
Data Index: 1746345 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.2561. Min Act: -0.1700
Data Index: 707456 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.2249. Min Act: -0.1700
Data Index: 6656720 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.2249. Min Act: -0.1700
Data Index: 6417854 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.0999. Min Act: -0.1700
Data Index: 4032965 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.0686. Min Act: -0.1700
Data Index: 7784972 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.0061. Min Act: -0.1700
Data Index: 6459784 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5374. Min Range: -5.5374
Max Act: 5.0061. Min Act: -0.1700
Data Index: 5788485 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9749. Min Act: -0.1700
Data Index: 7953847 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9749. Min Act: -0.1700
Data Index: 4381500 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9749. Min Act: -0.1700
Data Index: 7838789 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2882234 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9436. Min Act: -0.1700
Data Index: 7724969 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9436. Min Act: -0.1700
Data Index: 4662845 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9124. Min Act: -0.1700
Data Index: 5987775 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9124. Min Act: -0.1700
Data Index: 1803637 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.9436. Min Act: -0.1700
Data Index: 4790275 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5374. Min Range: -5.5374
Max Act: 4.8811. Min Act: -0.1700
Data Index: 4077911 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19