Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2174 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.9522. Min Act: -0.1700
Data Index: 922293 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.9209. Min Act: -0.1700
Data Index: 1711153 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 600774 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 6151031 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 5820578 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 1294293 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8584. Min Act: -0.1700
Data Index: 7067925 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6018869 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8584. Min Act: -0.1700
Data Index: 8615690 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8272. Min Act: -0.1700
Data Index: 5597349 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8272. Min Act: -0.1700
Data Index: 8137691 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7959. Min Act: -0.1700
Data Index: 3925629 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 4272537 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7959. Min Act: -0.1700
Data Index: 6566431 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7959. Min Act: -0.1700
Data Index: 7324535 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 7996301 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 7661183 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7959. Min Act: -0.1700
Data Index: 3335112 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 2381876 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7959. Min Act: -0.1700
Data Index: 413033 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19