Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2358 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.8441. Min Act: -0.1700
Data Index: 6509148 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.7503. Min Act: -0.1700
Data Index: 8105658 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.6253. Min Act: -0.1700
Data Index: 2772736 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.5316. Min Act: -0.1700
Data Index: 3473381 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.5003. Min Act: -0.1700
Data Index: 6668322 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.4066. Min Act: -0.1700
Data Index: 1639854 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.3753. Min Act: -0.1700
Data Index: 8201103 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.2816. Min Act: -0.1700
Data Index: 6600660 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.2816. Min Act: -0.1700
Data Index: 7103774 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4590079 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.2503. Min Act: -0.1700
Data Index: 6491980 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.2503. Min Act: -0.1700
Data Index: 6594674 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1878. Min Act: -0.1700
Data Index: 1074237 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1878. Min Act: -0.1700
Data Index: 7585221 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1878. Min Act: -0.1700
Data Index: 6936795 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1878. Min Act: -0.1700
Data Index: 512615 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1878. Min Act: -0.1700
Data Index: 1210192 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1566. Min Act: -0.1700
Data Index: 5769088 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1878. Min Act: -0.1700
Data Index: 5115640 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8441. Min Range: -5.8441
Max Act: 5.1878. Min Act: -0.1700
Data Index: 3000734 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19