Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.8751. Min Act: -0.1700
Data Index: 8142389 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.8751. Min Act: -0.1700
Data Index: 461541 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.7501. Min Act: -0.1700
Data Index: 1984611 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.7501. Min Act: -0.1700
Data Index: 1140576 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.6564. Min Act: -0.1700
Data Index: 1529107 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.6564. Min Act: -0.1700
Data Index: 8442832 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5939. Min Act: -0.1700
Data Index: 8507602 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5939. Min Act: -0.1700
Data Index: 3730974 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5939. Min Act: -0.1700
Data Index: 1174100 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.6251. Min Act: -0.1700
Data Index: 7138289 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5939. Min Act: -0.1700
Data Index: 5588240 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5001. Min Act: -0.1700
Data Index: 3897172 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5314. Min Act: -0.1700
Data Index: 1119706 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.4689. Min Act: -0.1700
Data Index: 2742651 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5001. Min Act: -0.1700
Data Index: 8751790 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5001. Min Act: -0.1700
Data Index: 173253 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.5001. Min Act: -0.1700
Data Index: 5335528 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.4689. Min Act: -0.1700
Data Index: 5080292 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.4376. Min Act: -0.1700
Data Index: 6601467 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8751. Min Range: -6.8751
Max Act: 6.4689. Min Act: -0.1700
Data Index: 2609669 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19