Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6255 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7212. Min Range: -8.7212
Max Act: 8.7212. Min Act: -0.1700
Data Index: 5873057 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7212. Min Range: -8.7212
Max Act: 8.4087. Min Act: -0.1700
Data Index: 7327830 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7212. Min Range: -8.7212
Max Act: 8.2837. Min Act: -0.1700
Data Index: 6435263 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7212. Min Range: -8.7212
Max Act: 8.0962. Min Act: -0.1700
Data Index: 4553565 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.9712. Min Act: -0.1700
Data Index: 3734588 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7212. Min Range: -8.7212
Max Act: 8.0337. Min Act: -0.1700
Data Index: 6459582 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7212. Min Range: -8.7212
Max Act: 8.0337. Min Act: -0.1700
Data Index: 4983133 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.9712. Min Act: -0.1700
Data Index: 7487306 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.9712. Min Act: -0.1700
Data Index: 4957794 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.9400. Min Act: -0.1700
Data Index: 1570629 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.8775. Min Act: -0.1700
Data Index: 1240804 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.9400. Min Act: -0.1700
Data Index: 3295375 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.8775. Min Act: -0.1700
Data Index: 4764109 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.7525. Min Act: -0.1700
Data Index: 1470074 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.7837. Min Act: -0.1700
Data Index: 6277617 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.7525. Min Act: -0.1700
Data Index: 1583003 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.7212. Min Act: -0.1700
Data Index: 6244536 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.7212. Min Act: -0.1700
Data Index: 7264501 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.6900. Min Act: -0.1700
Data Index: 4597262 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7212. Min Range: -8.7212
Max Act: 7.6900. Min Act: -0.1700
Data Index: 4693021 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19