Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5807 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.9074. Min Act: -0.1700
Data Index: 6926354 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.7824. Min Act: -0.1700
Data Index: 4049516 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.5324. Min Act: -0.1700
Data Index: 348781 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.5012. Min Act: -0.1700
Data Index: 7307508 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.5012. Min Act: -0.1700
Data Index: 2373895 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.4074. Min Act: -0.1700
Data Index: 8593375 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.4074. Min Act: -0.1700
Data Index: 8699219 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.3762. Min Act: -0.1700
Data Index: 2411262 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.3449. Min Act: -0.1700
Data Index: 4005011 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.2824. Min Act: -0.1700
Data Index: 7307499 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.2824. Min Act: -0.1700
Data Index: 3430915 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.2824. Min Act: -0.1700
Data Index: 7894365 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.2512. Min Act: -0.1700
Data Index: 7167893 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.1887. Min Act: -0.1700
Data Index: 3605893 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.2199. Min Act: -0.1700
Data Index: 5351246 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.1574. Min Act: -0.1700
Data Index: 5284314 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.0949. Min Act: -0.1700
Data Index: 643244 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.0949. Min Act: -0.1700
Data Index: 987402 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.1574. Min Act: -0.1700
Data Index: 7307495 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9074. Min Range: -6.9074
Max Act: 6.0949. Min Act: -0.1700
Data Index: 8111579 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19