Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.4210. Min Act: -0.1700
Data Index: 3937678 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.2335. Min Act: -0.1700
Data Index: 6641915 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.2022. Min Act: -0.1700
Data Index: 7070054 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.1397. Min Act: -0.1700
Data Index: 1634594 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.1397. Min Act: -0.1700
Data Index: 2797488 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.1085. Min Act: -0.1700
Data Index: 1137911 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.0772. Min Act: -0.1700
Data Index: 7615874 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.0772. Min Act: -0.1700
Data Index: 8326627 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.0460. Min Act: -0.1700
Data Index: 4698361 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.0460. Min Act: -0.1700
Data Index: 5446391 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.0772. Min Act: -0.1700
Data Index: 1075105 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.0460. Min Act: -0.1700
Data Index: 469432 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4210. Min Range: -6.4210
Max Act: 5.9835. Min Act: -0.1700
Data Index: 16973 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4210. Min Range: -6.4210
Max Act: 5.9835. Min Act: -0.1700
Data Index: 7503887 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4210. Min Range: -6.4210
Max Act: 5.9835. Min Act: -0.1700
Data Index: 2421993 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4210. Min Range: -6.4210
Max Act: 5.9835. Min Act: -0.1700
Data Index: 6139788 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4210. Min Range: -6.4210
Max Act: 5.9835. Min Act: -0.1700
Data Index: 2087182 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4210. Min Range: -6.4210
Max Act: 6.0147. Min Act: -0.1700
Data Index: 7830517 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4210. Min Range: -6.4210
Max Act: 5.9835. Min Act: -0.1700
Data Index: 6520996 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4210. Min Range: -6.4210
Max Act: 5.9522. Min Act: -0.1700
Data Index: 784355 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19