Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2821. Min Range: -7.2821
Max Act: 7.2821. Min Act: -0.1700
Data Index: 7077492 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2821. Min Range: -7.2821
Max Act: 7.1259. Min Act: -0.1700
Data Index: 8134400 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2821. Min Range: -7.2821
Max Act: 7.0634. Min Act: -0.1700
Data Index: 7056097 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2821. Min Range: -7.2821
Max Act: 7.0009. Min Act: -0.1700
Data Index: 7687282 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.9696. Min Act: -0.1700
Data Index: 4153175 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.9071. Min Act: -0.1700
Data Index: 194796 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.8446. Min Act: -0.1700
Data Index: 4287878 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.8759. Min Act: -0.1700
Data Index: 1124103 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.8759. Min Act: -0.1700
Data Index: 3975892 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.7509. Min Act: -0.1700
Data Index: 8455368 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.7509. Min Act: -0.1700
Data Index: 3702731 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.7509. Min Act: -0.1700
Data Index: 1110644 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.7196. Min Act: -0.1700
Data Index: 4336641 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.6884. Min Act: -0.1700
Data Index: 1788048 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.6884. Min Act: -0.1700
Data Index: 507552 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.6884. Min Act: -0.1700
Data Index: 2690041 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.6571. Min Act: -0.1700
Data Index: 7359229 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.6571. Min Act: -0.1700
Data Index: 2469538 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.5946. Min Act: -0.1700
Data Index: 1918272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.6259. Min Act: -0.1700
Data Index: 7969161 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19