Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2750 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4313. Min Range: -8.4313
Max Act: 8.4313. Min Act: -0.1700
Data Index: 6650602 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4313. Min Range: -8.4313
Max Act: 8.1813. Min Act: -0.1700
Data Index: 6712593 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4313. Min Range: -8.4313
Max Act: 8.1813. Min Act: -0.1700
Data Index: 3000258 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4313. Min Range: -8.4313
Max Act: 8.0250. Min Act: -0.1700
Data Index: 338051 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.9000. Min Act: -0.1700
Data Index: 2213969 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.7750. Min Act: -0.1700
Data Index: 2480910 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.7750. Min Act: -0.1700
Data Index: 5415740 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.7125. Min Act: -0.1700
Data Index: 516909 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.7438. Min Act: -0.1700
Data Index: 6060495 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.7438. Min Act: -0.1700
Data Index: 3644854 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.7125. Min Act: -0.1700
Data Index: 4442662 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.6813. Min Act: -0.1700
Data Index: 7232873 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.6500. Min Act: -0.1700
Data Index: 1751857 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.6188. Min Act: -0.1700
Data Index: 518825 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.6500. Min Act: -0.1700
Data Index: 807112 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 4830270 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 3488391 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.5250. Min Act: -0.1700
Data Index: 1682193 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 4853100 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4313. Min Range: -8.4313
Max Act: 7.4938. Min Act: -0.1700
Data Index: 112866 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19