Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3924. Min Range: -6.3924
Max Act: 6.3924. Min Act: -0.1700
Data Index: 561762 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3924. Min Range: -6.3924
Max Act: 6.0487. Min Act: -0.1700
Data Index: 1485018 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3924. Min Range: -6.3924
Max Act: 6.0487. Min Act: -0.1700
Data Index: 3212144 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3924. Min Range: -6.3924
Max Act: 6.0174. Min Act: -0.1700
Data Index: 988362 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3924. Min Range: -6.3924
Max Act: 6.0174. Min Act: -0.1700
Data Index: 4725164 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.9549. Min Act: -0.1700
Data Index: 6255547 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.9237. Min Act: -0.1700
Data Index: 8112139 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.9549. Min Act: -0.1700
Data Index: 5613039 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.9237. Min Act: -0.1700
Data Index: 4638126 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.9237. Min Act: -0.1700
Data Index: 1854586 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.9237. Min Act: -0.1700
Data Index: 8687190 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8924. Min Act: -0.1700
Data Index: 4926800 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8924. Min Act: -0.1700
Data Index: 4926823 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8299. Min Act: -0.1700
Data Index: 7683658 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8612. Min Act: -0.1700
Data Index: 6147645 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8612. Min Act: -0.1700
Data Index: 7299188 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8299. Min Act: -0.1700
Data Index: 4453761 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8299. Min Act: -0.1700
Data Index: 7622572 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.8299. Min Act: -0.1700
Data Index: 3094846 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3924. Min Range: -6.3924
Max Act: 5.7987. Min Act: -0.1700
Data Index: 7677724 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19