Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3149. Min Range: -6.3149
Max Act: 6.2836. Min Act: -0.1700
Data Index: 5190610 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3149. Min Range: -6.3149
Max Act: 6.3149. Min Act: -0.1700
Data Index: 1839133 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3149. Min Range: -6.3149
Max Act: 6.0649. Min Act: -0.1700
Data Index: 8070693 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3149. Min Range: -6.3149
Max Act: 6.0336. Min Act: -0.1700
Data Index: 1870654 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.9711. Min Act: -0.1700
Data Index: 4861141 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.9086. Min Act: -0.1700
Data Index: 7231807 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.9086. Min Act: -0.1700
Data Index: 5927159 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.8774. Min Act: -0.1700
Data Index: 3927084 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.8149. Min Act: -0.1700
Data Index: 2230226 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.8461. Min Act: -0.1700
Data Index: 971269 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7836. Min Act: -0.1700
Data Index: 3128044 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.8461. Min Act: -0.1700
Data Index: 2718184 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.8149. Min Act: -0.1700
Data Index: 2799661 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7836. Min Act: -0.1700
Data Index: 5672991 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7836. Min Act: -0.1700
Data Index: 2289278 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7836. Min Act: -0.1700
Data Index: 7402548 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7524. Min Act: -0.1700
Data Index: 5850988 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7524. Min Act: -0.1700
Data Index: 8454383 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7524. Min Act: -0.1700
Data Index: 6211419 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3149. Min Range: -6.3149
Max Act: 5.7211. Min Act: -0.1700
Data Index: 3732127 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19