Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0986. Min Range: -5.0986
Max Act: 5.0986. Min Act: -0.1700
Data Index: 3915481 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.9111. Min Act: -0.1700
Data Index: 6153907 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6409343 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.8486. Min Act: -0.1700
Data Index: 4408518 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.8486. Min Act: -0.1700
Data Index: 2768329 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.8486. Min Act: -0.1700
Data Index: 6420367 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.7548. Min Act: -0.1700
Data Index: 3069044 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.7236. Min Act: -0.1700
Data Index: 7942672 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.7236. Min Act: -0.1700
Data Index: 3398923 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6923. Min Act: -0.1700
Data Index: 604575 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6923. Min Act: -0.1700
Data Index: 1627679 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6611. Min Act: -0.1700
Data Index: 421110 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6923. Min Act: -0.1700
Data Index: 4949004 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6611. Min Act: -0.1700
Data Index: 332663 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6611. Min Act: -0.1700
Data Index: 7831126 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6611. Min Act: -0.1700
Data Index: 4252051 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6611. Min Act: -0.1700
Data Index: 8751956 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6611. Min Act: -0.1700
Data Index: 1498481 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6298. Min Act: -0.1700
Data Index: 1594535 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0986. Min Range: -5.0986
Max Act: 4.6298. Min Act: -0.1700
Data Index: 2466596 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19