Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4041. Min Range: -9.4041
Max Act: 9.4041. Min Act: -0.1700
Data Index: 8469855 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.7166. Min Act: -0.1700
Data Index: 1281353 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.6541. Min Act: -0.1700
Data Index: 2160723 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.5291. Min Act: -0.1700
Data Index: 5135448 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.4666. Min Act: -0.1700
Data Index: 5185107 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.4041. Min Act: -0.1700
Data Index: 6379431 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.2479. Min Act: -0.1700
Data Index: 2259175 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.1541. Min Act: -0.1700
Data Index: 6108909 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.1854. Min Act: -0.1700
Data Index: 6652212 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.1854. Min Act: -0.1700
Data Index: 6108910 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.0916. Min Act: -0.1700
Data Index: 6846651 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.0604. Min Act: -0.1700
Data Index: 8070611 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4041. Min Range: -9.4041
Max Act: 8.0291. Min Act: -0.1700
Data Index: 8352948 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4041. Min Range: -9.4041
Max Act: 7.9979. Min Act: -0.1700
Data Index: 8417140 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4041. Min Range: -9.4041
Max Act: 7.9666. Min Act: -0.1700
Data Index: 1401720 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4041. Min Range: -9.4041
Max Act: 7.9354. Min Act: -0.1700
Data Index: 1992745 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4041. Min Range: -9.4041
Max Act: 7.9666. Min Act: -0.1700
Data Index: 1153359 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4041. Min Range: -9.4041
Max Act: 7.9354. Min Act: -0.1700
Data Index: 8257188 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4041. Min Range: -9.4041
Max Act: 7.9354. Min Act: -0.1700
Data Index: 4903815 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4041. Min Range: -9.4041
Max Act: 7.9354. Min Act: -0.1700
Data Index: 2252111 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19