Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.9552. Min Act: -0.1700
Data Index: 4290713 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.4552. Min Act: -0.1700
Data Index: 7313603 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.4552. Min Act: -0.1700
Data Index: 4243074 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.4240. Min Act: -0.1700
Data Index: 5413197 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.4240. Min Act: -0.1700
Data Index: 3245756 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.4240. Min Act: -0.1700
Data Index: 5548185 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.3927. Min Act: -0.1700
Data Index: 6357630 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.2677. Min Act: -0.1700
Data Index: 6543023 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.1115. Min Act: -0.1700
Data Index: 2948597 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.1115. Min Act: -0.1700
Data Index: 4046368 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.1115. Min Act: -0.1700
Data Index: 188366 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.1115. Min Act: -0.1700
Data Index: 597342 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.1115. Min Act: -0.1700
Data Index: 5366645 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.0177. Min Act: -0.1700
Data Index: 2700829 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9552. Min Range: -7.9552
Max Act: 6.9865. Min Act: -0.1700
Data Index: 4548892 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9552. Min Range: -7.9552
Max Act: 6.9865. Min Act: -0.1700
Data Index: 7879669 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9552. Min Range: -7.9552
Max Act: 7.0177. Min Act: -0.1700
Data Index: 2376039 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9552. Min Range: -7.9552
Max Act: 6.9552. Min Act: -0.1700
Data Index: 7640372 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9552. Min Range: -7.9552
Max Act: 6.8927. Min Act: -0.1700
Data Index: 546134 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9552. Min Range: -7.9552
Max Act: 6.9240. Min Act: -0.1700
Data Index: 7630535 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19