Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5662 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.7357. Min Act: -0.1700
Data Index: 3934907 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.7044. Min Act: -0.1700
Data Index: 1619335 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5323. Min Act: -0.1700
Data Index: 4958075 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5323. Min Act: -0.1700
Data Index: 7232422 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4853. Min Act: -0.1700
Data Index: 7082414 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4540. Min Act: -0.1700
Data Index: 1850721 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4383. Min Act: -0.1700
Data Index: 8058198 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4383. Min Act: -0.1700
Data Index: 1335148 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4383. Min Act: -0.1700
Data Index: 4236298 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4226. Min Act: -0.1700
Data Index: 7381850 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4226. Min Act: -0.1700
Data Index: 3006448 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4069. Min Act: -0.1700
Data Index: 6771860 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4069. Min Act: -0.1700
Data Index: 1467378 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.3913. Min Act: -0.1700
Data Index: 5746467 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.3913. Min Act: -0.1700
Data Index: 5039158 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.3913. Min Act: -0.1700
Data Index: 8707744 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.3756. Min Act: -0.1700
Data Index: 2233092 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.3913. Min Act: -0.1700
Data Index: 1563356 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.3599. Min Act: -0.1700
Data Index: 8409201 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.3599. Min Act: -0.1700
Data Index: 2183899 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19