Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.4372. Min Act: -0.1700
Data Index: 483438 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.2497. Min Act: -0.1700
Data Index: 3328256 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.1559. Min Act: -0.1700
Data Index: 5725164 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.1247. Min Act: -0.1700
Data Index: 1280733 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.0934. Min Act: -0.1700
Data Index: 2674187 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.0934. Min Act: -0.1700
Data Index: 1893326 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.1247. Min Act: -0.1700
Data Index: 3770605 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.0309. Min Act: -0.1700
Data Index: 3485618 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.0622. Min Act: -0.1700
Data Index: 5282542 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.9997. Min Act: -0.1700
Data Index: 709571 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4372. Min Range: -7.4372
Max Act: 7.0309. Min Act: -0.1700
Data Index: 7850090 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.9684. Min Act: -0.1700
Data Index: 233149 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.9372. Min Act: -0.1700
Data Index: 991392 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.8747. Min Act: -0.1700
Data Index: 1652196 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.8747. Min Act: -0.1700
Data Index: 744380 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.8747. Min Act: -0.1700
Data Index: 53490 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.8122. Min Act: -0.1700
Data Index: 8337632 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.8434. Min Act: -0.1700
Data Index: 6512642 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.8122. Min Act: -0.1700
Data Index: 6989863 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4372. Min Range: -7.4372
Max Act: 6.8122. Min Act: -0.1700
Data Index: 2919842 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19