Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1901. Min Range: -4.1901
Max Act: 4.1901. Min Act: -0.1700
Data Index: 2087543 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1901. Min Range: -4.1901
Max Act: 4.0963. Min Act: -0.1700
Data Index: 8228538 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1901. Min Range: -4.1901
Max Act: 4.0338. Min Act: -0.1700
Data Index: 4547922 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9713. Min Act: -0.1700
Data Index: 6173369 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 1741595 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 4343565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 1021527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 6825614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 4112894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 4938394 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 6866232 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 733268 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.9088. Min Act: -0.1700
Data Index: 8072019 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.8775. Min Act: -0.1700
Data Index: 3806353 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.8463. Min Act: -0.1700
Data Index: 3358774 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.7524. Min Act: -0.1700
Data Index: 4135094 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.7524. Min Act: -0.1700
Data Index: 3965017 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.7524. Min Act: -0.1700
Data Index: 7754708 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.6899. Min Act: -0.1700
Data Index: 1313866 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1901. Min Range: -4.1901
Max Act: 3.7211. Min Act: -0.1700
Data Index: 337309 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19