Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1481 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.5059. Min Act: -0.1700
Data Index: 8424078 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.4434. Min Act: -0.1700
Data Index: 4237443 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3809. Min Act: -0.1700
Data Index: 4699736 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3809. Min Act: -0.1700
Data Index: 6139877 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3809. Min Act: -0.1700
Data Index: 2926353 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 3281456 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3497. Min Act: -0.1700
Data Index: 2175673 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3497. Min Act: -0.1699
Data Index: 6188935 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2559. Min Act: -0.1699
Data Index: 2451930 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2872. Min Act: -0.1700
Data Index: 8719237 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2872. Min Act: -0.1700
Data Index: 8543651 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2559. Min Act: -0.1700
Data Index: 1268977 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2559. Min Act: -0.1700
Data Index: 2985380 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2559. Min Act: -0.1700
Data Index: 1035096 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2247. Min Act: -0.1700
Data Index: 6757261 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2247. Min Act: -0.1700
Data Index: 8362159 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1934. Min Act: -0.1700
Data Index: 1053184 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1934. Min Act: -0.1700
Data Index: 3668586 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1622. Min Act: -0.1700
Data Index: 6124887 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1934. Min Act: -0.1700
Data Index: 8411570 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19