Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6227. Min Range: -8.6227
Max Act: 8.6227. Min Act: -0.1700
Data Index: 228204 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6227. Min Range: -8.6227
Max Act: 8.6227. Min Act: -0.1700
Data Index: 228202 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.3727. Min Act: -0.1700
Data Index: 5463812 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.3415. Min Act: -0.1700
Data Index: 8105014 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.2790. Min Act: -0.1700
Data Index: 7468602 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.0915. Min Act: -0.1700
Data Index: 2239107 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.0290. Min Act: -0.1700
Data Index: 3182253 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.0602. Min Act: -0.1700
Data Index: 8637421 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.0602. Min Act: -0.1700
Data Index: 1235083 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.0290. Min Act: -0.1700
Data Index: 1543440 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.0290. Min Act: -0.1699
Data Index: 743800 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6227. Min Range: -8.6227
Max Act: 7.0290. Min Act: -0.1700
Data Index: 8032510 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.9977. Min Act: -0.1700
Data Index: 7067470 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.9977. Min Act: -0.1700
Data Index: 425298 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.9977. Min Act: -0.1700
Data Index: 93270 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.9352. Min Act: -0.1700
Data Index: 912425 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.9352. Min Act: -0.1700
Data Index: 2878472 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.9040. Min Act: -0.1700
Data Index: 2191730 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.8727. Min Act: -0.1700
Data Index: 4716692 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6227. Min Range: -8.6227
Max Act: 6.9040. Min Act: -0.1700
Data Index: 465021 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19