Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 448 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.9639. Min Act: -0.1700
Data Index: 4014312 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.8077. Min Act: -0.1700
Data Index: 2860647 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.7139. Min Act: -0.1700
Data Index: 1192135 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.6514. Min Act: -0.1700
Data Index: 7511444 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.6202. Min Act: -0.1700
Data Index: 1378850 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.5577. Min Act: -0.1700
Data Index: 7559832 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.5577. Min Act: -0.1700
Data Index: 7418818 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4952. Min Act: -0.1700
Data Index: 7275006 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4639. Min Act: -0.1700
Data Index: 3126117 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4327. Min Act: -0.1700
Data Index: 8386374 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4327. Min Act: -0.1700
Data Index: 1563801 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4639. Min Act: -0.1700
Data Index: 3288578 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4327. Min Act: -0.1700
Data Index: 486580 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4014. Min Act: -0.1700
Data Index: 2647965 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4014. Min Act: -0.1700
Data Index: 6589167 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4014. Min Act: -0.1700
Data Index: 8777219 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4014. Min Act: -0.1700
Data Index: 3799386 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.4014. Min Act: -0.1700
Data Index: 7258540 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.3702. Min Act: -0.1700
Data Index: 542780 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9639. Min Range: -5.9639
Max Act: 5.3702. Min Act: -0.1700
Data Index: 1479909 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19