Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3913. Min Act: -0.1700
Data Index: 2153237 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3756. Min Act: -0.1700
Data Index: 5320519 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3599. Min Act: -0.1700
Data Index: 7591297 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3756. Min Act: -0.1700
Data Index: 125493 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3442. Min Act: -0.1700
Data Index: 7262624 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3442. Min Act: -0.1700
Data Index: 4846327 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3285. Min Act: -0.1700
Data Index: 7425282 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2815. Min Act: -0.1700
Data Index: 207849 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.3129. Min Act: -0.1700
Data Index: 4326861 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2815. Min Act: -0.1700
Data Index: 5750681 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2815. Min Act: -0.1700
Data Index: 3520351 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2658. Min Act: -0.1700
Data Index: 903211 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2658. Min Act: -0.1700
Data Index: 588095 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2658. Min Act: -0.1700
Data Index: 6365802 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2500. Min Act: -0.1700
Data Index: 8385365 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2500. Min Act: -0.1700
Data Index: 1629394 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2500. Min Act: -0.1700
Data Index: 5700746 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2500. Min Act: -0.1700
Data Index: 5847173 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2343. Min Act: -0.1700
Data Index: 6806447 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3913. Min Range: -3.3913
Max Act: 3.2343. Min Act: -0.1700
Data Index: 5292109 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19