Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3979. Min Act: -0.1700
Data Index: 1951800 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3979. Min Act: -0.1700
Data Index: 204879 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3979. Min Act: -0.1700
Data Index: 98796 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3354. Min Act: -0.1700
Data Index: 3622251 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3666. Min Act: -0.1700
Data Index: 1727599 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3041. Min Act: -0.1700
Data Index: 3048704 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3041. Min Act: -0.1700
Data Index: 4401719 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3354. Min Act: -0.1700
Data Index: 8241874 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3354. Min Act: -0.1700
Data Index: 7249230 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3354. Min Act: -0.1700
Data Index: 2927118 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3041. Min Act: -0.1700
Data Index: 1544799 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 2668090 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 5228260 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 5563800 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 6412299 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.3041. Min Act: -0.1700
Data Index: 5082245 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 7705095 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 4713775 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 8494554 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3979. Min Range: -5.3979
Max Act: 5.2729. Min Act: -0.1700
Data Index: 4462917 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19