Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.3694. Min Act: -0.1700
Data Index: 7033644 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.3069. Min Act: -0.1700
Data Index: 2856157 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.3069. Min Act: -0.1700
Data Index: 1628732 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1819. Min Act: -0.1700
Data Index: 3965173 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1819. Min Act: -0.1700
Data Index: 8570305 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1819. Min Act: -0.1700
Data Index: 1207632 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1819. Min Act: -0.1700
Data Index: 5912292 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1194. Min Act: -0.1700
Data Index: 6431280 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1194. Min Act: -0.1700
Data Index: 2602498 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1194. Min Act: -0.1700
Data Index: 6667 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1194. Min Act: -0.1700
Data Index: 7127906 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1194. Min Act: -0.1700
Data Index: 7939480 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.0882. Min Act: -0.1700
Data Index: 3467779 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.0882. Min Act: -0.1700
Data Index: 6674918 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.1194. Min Act: -0.1700
Data Index: 2284218 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.0569. Min Act: -0.1700
Data Index: 668516 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.0882. Min Act: -0.1700
Data Index: 4868126 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.0882. Min Act: -0.1700
Data Index: 7165086 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.0569. Min Act: -0.1700
Data Index: 6118001 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3694. Min Range: -4.3694
Max Act: 4.0569. Min Act: -0.1700
Data Index: 1927057 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19