Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.3096. Min Act: -0.1700
Data Index: 1155118 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.1533. Min Act: -0.1700
Data Index: 6456924 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.1221. Min Act: -0.1700
Data Index: 2574741 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.1221. Min Act: -0.1700
Data Index: 2446986 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.1221. Min Act: -0.1700
Data Index: 3569317 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0908. Min Act: -0.1700
Data Index: 5154644 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0908. Min Act: -0.1700
Data Index: 5032420 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0908. Min Act: -0.1700
Data Index: 3602678 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0908. Min Act: -0.1700
Data Index: 4692762 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0908. Min Act: -0.1700
Data Index: 6250175 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0596. Min Act: -0.1700
Data Index: 6455427 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0596. Min Act: -0.1700
Data Index: 619869 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0596. Min Act: -0.1700
Data Index: 2085658 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0283. Min Act: -0.1700
Data Index: 2445812 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0283. Min Act: -0.1700
Data Index: 6180458 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0283. Min Act: -0.1700
Data Index: 4604174 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0283. Min Act: -0.1700
Data Index: 7940662 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3096. Min Range: -5.3096
Max Act: 4.9971. Min Act: -0.1700
Data Index: 1147123 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3096. Min Range: -5.3096
Max Act: 5.0283. Min Act: -0.1700
Data Index: 506390 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3096. Min Range: -5.3096
Max Act: 4.9971. Min Act: -0.1700
Data Index: 4277987 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19