Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2326 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.8952. Min Act: -0.1700
Data Index: 7005928 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.8327. Min Act: -0.1700
Data Index: 1629121 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.8327. Min Act: -0.1700
Data Index: 7174595 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.7390. Min Act: -0.1700
Data Index: 3477513 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.7077. Min Act: -0.1700
Data Index: 2944016 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.6765. Min Act: -0.1700
Data Index: 556854 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.6140. Min Act: -0.1700
Data Index: 1121425 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5827. Min Act: -0.1700
Data Index: 3905078 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5515. Min Act: -0.1700
Data Index: 2459472 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5515. Min Act: -0.1700
Data Index: 3877905 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5202. Min Act: -0.1700
Data Index: 7761312 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5202. Min Act: -0.1700
Data Index: 7796425 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5202. Min Act: -0.1700
Data Index: 5348434 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5202. Min Act: -0.1700
Data Index: 3652765 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5202. Min Act: -0.1700
Data Index: 842550 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.5202. Min Act: -0.1700
Data Index: 4369514 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.4890. Min Act: -0.1700
Data Index: 7056663 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.4890. Min Act: -0.1700
Data Index: 8133252 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.4577. Min Act: -0.1700
Data Index: 17672 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8952. Min Range: -5.8952
Max Act: 5.4577. Min Act: -0.1700
Data Index: 6336777 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19