Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.6701. Min Act: -0.1700
Data Index: 7193334 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.5764. Min Act: -0.1700
Data Index: 7566027 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4826. Min Act: -0.1700
Data Index: 7807569 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4514. Min Act: -0.1700
Data Index: 2056561 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4201. Min Act: -0.1700
Data Index: 2073562 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.3889. Min Act: -0.1700
Data Index: 7779373 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.3576. Min Act: -0.1700
Data Index: 7201210 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.3576. Min Act: -0.1700
Data Index: 892762 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.3576. Min Act: -0.1700
Data Index: 3739181 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.3264. Min Act: -0.1700
Data Index: 4486379 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2951. Min Act: -0.1700
Data Index: 5177748 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.3264. Min Act: -0.1700
Data Index: 3135855 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.3264. Min Act: -0.1700
Data Index: 3610885 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2951. Min Act: -0.1700
Data Index: 7733748 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2639. Min Act: -0.1700
Data Index: 6566912 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2639. Min Act: -0.1700
Data Index: 2148556 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2639. Min Act: -0.1700
Data Index: 6395496 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2639. Min Act: -0.1700
Data Index: 3471352 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2326. Min Act: -0.1700
Data Index: 1938655 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.2014. Min Act: -0.1700
Data Index: 6992412 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19