Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1466. Min Range: -7.1466
Max Act: 7.1466. Min Act: -0.1700
Data Index: 4648327 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1466. Min Range: -7.1466
Max Act: 7.0216. Min Act: -0.1700
Data Index: 4655722 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.8966. Min Act: -0.1700
Data Index: 7890034 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.8341. Min Act: -0.1700
Data Index: 4547019 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.7716. Min Act: -0.1700
Data Index: 8449921 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.5841. Min Act: -0.1700
Data Index: 2595306 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.5528. Min Act: -0.1700
Data Index: 4626263 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4903. Min Act: -0.1700
Data Index: 8790800 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.5216. Min Act: -0.1700
Data Index: 4132812 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.5216. Min Act: -0.1700
Data Index: 4957868 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.5216. Min Act: -0.1700
Data Index: 6224768 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4903. Min Act: -0.1700
Data Index: 8153166 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4278. Min Act: -0.1700
Data Index: 6512135 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3966. Min Act: -0.1700
Data Index: 1699086 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3653. Min Act: -0.1700
Data Index: 5052574 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3653. Min Act: -0.1700
Data Index: 6721764 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3653. Min Act: -0.1700
Data Index: 4970220 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3966. Min Act: -0.1700
Data Index: 2890617 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3653. Min Act: -0.1700
Data Index: 4045823 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3653. Min Act: -0.1700
Data Index: 5230094 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19