Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.3961. Min Act: -0.1700
Data Index: 6254800 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.2711. Min Act: -0.1700
Data Index: 4107587 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.0836. Min Act: -0.1700
Data Index: 628732 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.0836. Min Act: -0.1700
Data Index: 7081553 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.0523. Min Act: -0.1700
Data Index: 1783234 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.0523. Min Act: -0.1700
Data Index: 6918293 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.0211. Min Act: -0.1700
Data Index: 5922186 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3961. Min Range: -6.3961
Max Act: 6.0523. Min Act: -0.1700
Data Index: 2618314 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.9898. Min Act: -0.1700
Data Index: 5889349 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.9586. Min Act: -0.1700
Data Index: 6133494 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.9586. Min Act: -0.1700
Data Index: 6966679 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.9273. Min Act: -0.1700
Data Index: 7254618 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.9586. Min Act: -0.1700
Data Index: 7903804 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.8961. Min Act: -0.1700
Data Index: 7090287 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.8961. Min Act: -0.1700
Data Index: 4783866 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.9273. Min Act: -0.1700
Data Index: 2008535 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.8648. Min Act: -0.1700
Data Index: 1511100 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.8648. Min Act: -0.1700
Data Index: 5351840 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.8336. Min Act: -0.1700
Data Index: 1220133 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3961. Min Range: -6.3961
Max Act: 5.8336. Min Act: -0.1700
Data Index: 5933453 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19