Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6296 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0028. Min Range: -5.0028
Max Act: 5.0028. Min Act: -0.1700
Data Index: 3219434 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.8466. Min Act: -0.1700
Data Index: 2729535 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.8466. Min Act: -0.1700
Data Index: 164915 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.8153. Min Act: -0.1700
Data Index: 3265925 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.7528. Min Act: -0.1700
Data Index: 655667 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.7528. Min Act: -0.1700
Data Index: 5812169 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.7528. Min Act: -0.1700
Data Index: 6764311 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.7528. Min Act: -0.1700
Data Index: 6016639 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.7216. Min Act: -0.1700
Data Index: 1495496 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.7216. Min Act: -0.1700
Data Index: 6035262 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6903. Min Act: -0.1700
Data Index: 5049046 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6591. Min Act: -0.1700
Data Index: 3324481 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6903. Min Act: -0.1700
Data Index: 4102525 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6591. Min Act: -0.1700
Data Index: 3667890 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6591. Min Act: -0.1700
Data Index: 2302760 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6903. Min Act: -0.1700
Data Index: 2419661 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6278. Min Act: -0.1700
Data Index: 283503 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.5966. Min Act: -0.1700
Data Index: 1109755 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6278. Min Act: -0.1700
Data Index: 5703127 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0028. Min Range: -5.0028
Max Act: 4.6278. Min Act: -0.1700
Data Index: 4015367 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19