Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0202. Min Range: -9.0202
Max Act: 9.0202. Min Act: -0.1700
Data Index: 8410382 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.4577. Min Act: -0.1700
Data Index: 1675403 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.4577. Min Act: -0.1700
Data Index: 2921213 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.4264. Min Act: -0.1700
Data Index: 2969456 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.3639. Min Act: -0.1700
Data Index: 3482616 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.3014. Min Act: -0.1700
Data Index: 351889 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.3014. Min Act: -0.1700
Data Index: 5351403 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.3014. Min Act: -0.1700
Data Index: 2188213 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.3014. Min Act: -0.1700
Data Index: 1695712 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.2702. Min Act: -0.1700
Data Index: 2818200 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.1452. Min Act: -0.1700
Data Index: 4296811 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.2077. Min Act: -0.1700
Data Index: 7821787 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.1452. Min Act: -0.1700
Data Index: 213126 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.1139. Min Act: -0.1700
Data Index: 6495250 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.1452. Min Act: -0.1700
Data Index: 7973072 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.0827. Min Act: -0.1700
Data Index: 8237762 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.1452. Min Act: -0.1700
Data Index: 1186197 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.0827. Min Act: -0.1700
Data Index: 7110227 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.0827. Min Act: -0.1700
Data Index: 7016443 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0202. Min Range: -9.0202
Max Act: 8.0514. Min Act: -0.1700
Data Index: 252462 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19