Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.7022. Min Act: -0.1700
Data Index: 4770878 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.5772. Min Act: -0.1700
Data Index: 2468946 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.6085. Min Act: -0.1700
Data Index: 6579432 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.4835. Min Act: -0.1700
Data Index: 7228056 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.4835. Min Act: -0.1700
Data Index: 4407106 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.4522. Min Act: -0.1700
Data Index: 7089688 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.4522. Min Act: -0.1700
Data Index: 2717985 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.4210. Min Act: -0.1700
Data Index: 45493 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.4210. Min Act: -0.1700
Data Index: 6664711 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3897. Min Act: -0.1700
Data Index: 3028086 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3897. Min Act: -0.1700
Data Index: 1845092 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3585. Min Act: -0.1700
Data Index: 2028519 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3585. Min Act: -0.1700
Data Index: 8369421 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3585. Min Act: -0.1700
Data Index: 8177649 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3585. Min Act: -0.1700
Data Index: 8681678 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3585. Min Act: -0.1700
Data Index: 8536641 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.2960. Min Act: -0.1700
Data Index: 280085 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3272. Min Act: -0.1700
Data Index: 2555955 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3272. Min Act: -0.1700
Data Index: 351106 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7022. Min Range: -5.7022
Max Act: 5.3272. Min Act: -0.1700
Data Index: 1415633 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19