Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.9869. Min Act: -0.1700
Data Index: 932274 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.5494. Min Act: -0.1700
Data Index: 249367 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.4244. Min Act: -0.1700
Data Index: 2482036 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.4869. Min Act: -0.1700
Data Index: 5525261 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.4244. Min Act: -0.1700
Data Index: 1449849 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.4869. Min Act: -0.1700
Data Index: 7408399 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2994. Min Act: -0.1700
Data Index: 443470 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.3619. Min Act: -0.1700
Data Index: 5774545 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2994. Min Act: -0.1700
Data Index: 8490897 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2994. Min Act: -0.1700
Data Index: 4360524 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2994. Min Act: -0.1700
Data Index: 5208722 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.3619. Min Act: -0.1700
Data Index: 315090 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2369. Min Act: -0.1700
Data Index: 1907325 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.1744. Min Act: -0.1700
Data Index: 6297279 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.1744. Min Act: -0.1700
Data Index: 3238499 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2369. Min Act: -0.1700
Data Index: 2935853 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2369. Min Act: -0.1700
Data Index: 7395030 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2369. Min Act: -0.1700
Data Index: 7664630 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2369. Min Act: -0.1700
Data Index: 3705079 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9869. Min Range: -8.9869
Max Act: 8.2369. Min Act: -0.1700
Data Index: 1510875 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19