Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.7939. Min Act: -0.1700
Data Index: 665445 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.6376. Min Act: -0.1700
Data Index: 8749012 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.4501. Min Act: -0.1700
Data Index: 7567483 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.4501. Min Act: -0.1700
Data Index: 5873140 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.4189. Min Act: -0.1700
Data Index: 2448201 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3876. Min Act: -0.1700
Data Index: 2342067 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3564. Min Act: -0.1700
Data Index: 368009 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2626. Min Act: -0.1700
Data Index: 5742140 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2626. Min Act: -0.1700
Data Index: 7067121 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2939. Min Act: -0.1700
Data Index: 7281010 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2626. Min Act: -0.1700
Data Index: 4397798 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2314. Min Act: -0.1700
Data Index: 3799501 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2314. Min Act: -0.1700
Data Index: 731337 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2314. Min Act: -0.1700
Data Index: 7028870 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.1689. Min Act: -0.1700
Data Index: 1691739 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2001. Min Act: -0.1700
Data Index: 7899376 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.1064. Min Act: -0.1700
Data Index: 4437766 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.1376. Min Act: -0.1700
Data Index: 4099016 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.1376. Min Act: -0.1700
Data Index: 6603683 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.1064. Min Act: -0.1700
Data Index: 7689807 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19