Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1417 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0309. Min Range: -9.0309
Max Act: 9.0309. Min Act: -0.1700
Data Index: 1528218 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.9684. Min Act: -0.1700
Data Index: 4079281 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.7184. Min Act: -0.1700
Data Index: 1273422 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.5934. Min Act: -0.1700
Data Index: 7014370 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.4684. Min Act: -0.1700
Data Index: 8270270 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.4059. Min Act: -0.1700
Data Index: 1311693 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.3434. Min Act: -0.1700
Data Index: 299514 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.4059. Min Act: -0.1700
Data Index: 1130215 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.2809. Min Act: -0.1700
Data Index: 755788 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.2809. Min Act: -0.1700
Data Index: 6090732 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.1559. Min Act: -0.1700
Data Index: 5795017 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.1559. Min Act: -0.1699
Data Index: 6162058 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.1559. Min Act: -0.1700
Data Index: 724477 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.1559. Min Act: -0.1700
Data Index: 7799570 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.0934. Min Act: -0.1700
Data Index: 6327151 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.0309. Min Act: -0.1700
Data Index: 498600 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.0934. Min Act: -0.1700
Data Index: 7469050 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.0309. Min Act: -0.1700
Data Index: 7861048 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.0934. Min Act: -0.1700
Data Index: 2945333 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0309. Min Range: -9.0309
Max Act: 8.0934. Min Act: -0.1700
Data Index: 1565563 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19