Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.7735. Min Act: -0.1700
Data Index: 6762759 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.5860. Min Act: -0.1700
Data Index: 2824997 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.3360. Min Act: -0.1700
Data Index: 8305185 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.3360. Min Act: -0.1700
Data Index: 3586981 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.2735. Min Act: -0.1700
Data Index: 193274 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.2110. Min Act: -0.1700
Data Index: 2366241 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.2110. Min Act: -0.1700
Data Index: 7570621 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.2110. Min Act: -0.1700
Data Index: 8093549 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.1485. Min Act: -0.1700
Data Index: 4440550 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.1485. Min Act: -0.1700
Data Index: 3437840 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.1485. Min Act: -0.1700
Data Index: 2444833 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.1485. Min Act: -0.1700
Data Index: 1171584 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.1485. Min Act: -0.1700
Data Index: 2411401 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.0235. Min Act: -0.1700
Data Index: 83448 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.1485. Min Act: -0.1700
Data Index: 3139326 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.0860. Min Act: -0.1700
Data Index: 7012982 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.0860. Min Act: -0.1700
Data Index: 3979617 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7735. Min Range: -8.7735
Max Act: 7.9610. Min Act: -0.1700
Data Index: 527330 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.0235. Min Act: -0.1700
Data Index: 3521301 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7735. Min Range: -8.7735
Max Act: 8.0235. Min Act: -0.1700
Data Index: 2431854 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19