Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4413 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.1726. Min Act: -0.1700
Data Index: 1561225 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.1413. Min Act: -0.1700
Data Index: 7318130 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.1101. Min Act: -0.1700
Data Index: 5819548 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 8469738 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 596646 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 2376453 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.0476. Min Act: -0.1700
Data Index: 7967318 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.0476. Min Act: -0.1700
Data Index: 415521 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.0163. Min Act: -0.1700
Data Index: 1987014 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1726. Min Range: -5.1726
Max Act: 5.0163. Min Act: -0.1700
Data Index: 8294402 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9851. Min Act: -0.1700
Data Index: 4870673 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9851. Min Act: -0.1700
Data Index: 5481945 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9538. Min Act: -0.1700
Data Index: 5306841 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9538. Min Act: -0.1700
Data Index: 7830966 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.8913. Min Act: -0.1700
Data Index: 7184285 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9226. Min Act: -0.1700
Data Index: 3251298 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9538. Min Act: -0.1700
Data Index: 6918410 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9226. Min Act: -0.1700
Data Index: 108346 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9226. Min Act: -0.1700
Data Index: 5653169 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1726. Min Range: -5.1726
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2177677 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19