Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.5649. Min Act: -0.1700
Data Index: 3569070 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4248555 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.5024. Min Act: -0.1700
Data Index: 169893 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.4087. Min Act: -0.1700
Data Index: 400358 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2776600 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3774. Min Act: -0.1700
Data Index: 5418643 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3149. Min Act: -0.1700
Data Index: 6473764 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3149. Min Act: -0.1700
Data Index: 2995697 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2212. Min Act: -0.1700
Data Index: 8510306 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2524. Min Act: -0.1700
Data Index: 2449511 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2212. Min Act: -0.1700
Data Index: 2854416 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2212. Min Act: -0.1700
Data Index: 1270344 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2212. Min Act: -0.1700
Data Index: 354811 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.1899. Min Act: -0.1700
Data Index: 1016936 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.1587. Min Act: -0.1700
Data Index: 6016423 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.1274. Min Act: -0.1700
Data Index: 7868308 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.1274. Min Act: -0.1700
Data Index: 3319520 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.0962. Min Act: -0.1700
Data Index: 3843977 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.0962. Min Act: -0.1700
Data Index: 417295 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.0962. Min Act: -0.1700
Data Index: 6006128 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19