Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4861 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.8570. Min Act: -0.1700
Data Index: 6456459 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.4188. Min Act: -0.1700
Data Index: 743326 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.3717. Min Act: -0.1700
Data Index: 6172514 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.3561. Min Act: -0.1700
Data Index: 8684813 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.3717. Min Act: -0.1700
Data Index: 1352147 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.3247. Min Act: -0.1700
Data Index: 878457 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.3247. Min Act: -0.1700
Data Index: 5441353 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.3090. Min Act: -0.1700
Data Index: 7118183 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2933. Min Act: -0.1700
Data Index: 4523292 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2462. Min Act: -0.1700
Data Index: 6781050 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2304. Min Act: -0.1700
Data Index: 2479635 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2304. Min Act: -0.1700
Data Index: 5261466 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2304. Min Act: -0.1700
Data Index: 4216692 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2304. Min Act: -0.1700
Data Index: 4450125 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2147. Min Act: -0.1700
Data Index: 420280 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.2304. Min Act: -0.1700
Data Index: 5511442 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.1990. Min Act: -0.1700
Data Index: 788168 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.1990. Min Act: -0.1700
Data Index: 5775200 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.1833. Min Act: -0.1700
Data Index: 4931263 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.1990. Min Act: -0.1700
Data Index: 1718312 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19