Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.4304. Min Act: -0.1700
Data Index: 108515 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3833. Min Act: -0.1700
Data Index: 1799564 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3520. Min Act: -0.1700
Data Index: 7627319 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3677. Min Act: -0.1700
Data Index: 8130550 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3206. Min Act: -0.1700
Data Index: 6808861 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2892. Min Act: -0.1700
Data Index: 3455108 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2892. Min Act: -0.1700
Data Index: 6059029 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2578. Min Act: -0.1700
Data Index: 662470 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2421. Min Act: -0.1700
Data Index: 3652531 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.2421. Min Act: -0.1700
Data Index: 3748058 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1792. Min Act: -0.1700
Data Index: 4503105 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1634. Min Act: -0.1699
Data Index: 2389170 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1634. Min Act: -0.1700
Data Index: 1714049 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1634. Min Act: -0.1700
Data Index: 4503096 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1477. Min Act: -0.1700
Data Index: 6928755 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1634. Min Act: -0.1700
Data Index: 6854890 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1477. Min Act: -0.1700
Data Index: 789545 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1162. Min Act: -0.1700
Data Index: 4530902 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1320. Min Act: -0.1700
Data Index: 3573416 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.1162. Min Act: -0.1700
Data Index: 4022076 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19