Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1948 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3475. Min Range: -6.3475
Max Act: 6.3475. Min Act: -0.1700
Data Index: 7641941 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3475. Min Range: -6.3475
Max Act: 6.2225. Min Act: -0.1700
Data Index: 8640892 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3475. Min Range: -6.3475
Max Act: 6.0350. Min Act: -0.1700
Data Index: 2945689 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3475. Min Range: -6.3475
Max Act: 6.0038. Min Act: -0.1700
Data Index: 3384382 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9725. Min Act: -0.1700
Data Index: 8795675 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9725. Min Act: -0.1700
Data Index: 5924179 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9100. Min Act: -0.1700
Data Index: 3998085 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9413. Min Act: -0.1700
Data Index: 8083566 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9100. Min Act: -0.1700
Data Index: 2228364 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9100. Min Act: -0.1700
Data Index: 4524346 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9413. Min Act: -0.1700
Data Index: 5270226 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.9100. Min Act: -0.1700
Data Index: 4894403 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.8788. Min Act: -0.1700
Data Index: 684586 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.8475. Min Act: -0.1700
Data Index: 3494150 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.8475. Min Act: -0.1700
Data Index: 2221173 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6748815 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.7850. Min Act: -0.1700
Data Index: 5388927 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.8163. Min Act: -0.1700
Data Index: 8001091 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.7850. Min Act: -0.1700
Data Index: 1043025 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3475. Min Range: -6.3475
Max Act: 5.8163. Min Act: -0.1700
Data Index: 2925277 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19