Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0202. Min Range: -5.0202
Max Act: 5.0202. Min Act: -0.1696
Data Index: 7240344 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.9577. Min Act: -0.1700
Data Index: 1587867 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.9264. Min Act: -0.1700
Data Index: 5513489 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8952. Min Act: -0.1700
Data Index: 615182 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8952. Min Act: -0.1700
Data Index: 2216464 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8639. Min Act: -0.1700
Data Index: 3309834 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8639. Min Act: -0.1700
Data Index: 3357300 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8639. Min Act: -0.1700
Data Index: 6210976 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 4522762 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8639. Min Act: -0.1700
Data Index: 5366690 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8639. Min Act: -0.1700
Data Index: 1509560 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 7267412 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 8681874 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8639. Min Act: -0.1700
Data Index: 927167 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 8388638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 7394856 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 1081145 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 2533982 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1698
Data Index: 711927 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0202. Min Range: -5.0202
Max Act: 4.8327. Min Act: -0.1700
Data Index: 1293344 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19