Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4096. Min Range: -4.4096
Max Act: 4.4096. Min Act: -0.1700
Data Index: 6277783 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4096. Min Range: -4.4096
Max Act: 4.0970. Min Act: -0.1700
Data Index: 912260 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4096. Min Range: -4.4096
Max Act: 4.0970. Min Act: -0.1700
Data Index: 1007524 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4096. Min Range: -4.4096
Max Act: 4.0658. Min Act: -0.1700
Data Index: 7635786 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4096. Min Range: -4.4096
Max Act: 4.0658. Min Act: -0.1700
Data Index: 2903199 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4096. Min Range: -4.4096
Max Act: 4.0345. Min Act: -0.1700
Data Index: 5237571 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4096. Min Range: -4.4096
Max Act: 4.0032. Min Act: -0.1700
Data Index: 2127055 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.9720. Min Act: -0.1700
Data Index: 8231161 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.9407. Min Act: -0.1700
Data Index: 774668 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.9407. Min Act: -0.1700
Data Index: 6515225 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.9407. Min Act: -0.1700
Data Index: 1264473 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.9095. Min Act: -0.1700
Data Index: 2250805 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8782. Min Act: -0.1700
Data Index: 1333507 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8782. Min Act: -0.1700
Data Index: 23905 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8782. Min Act: -0.1700
Data Index: 2051568 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8782. Min Act: -0.1700
Data Index: 1377963 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8469. Min Act: -0.1700
Data Index: 6127335 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8469. Min Act: -0.1700
Data Index: 5602868 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8469. Min Act: -0.1700
Data Index: 7318649 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4096. Min Range: -4.4096
Max Act: 3.8469. Min Act: -0.1700
Data Index: 5843369 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19