Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2136. Min Range: -8.2136
Max Act: 8.2136. Min Act: -0.1700
Data Index: 4236460 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.8386. Min Act: -0.1700
Data Index: 3666 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.7761. Min Act: -0.1700
Data Index: 2946164 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.7761. Min Act: -0.1700
Data Index: 6583602 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.6511. Min Act: -0.1700
Data Index: 4038251 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.6511. Min Act: -0.1700
Data Index: 6014378 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.6511. Min Act: -0.1700
Data Index: 4284753 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.6511. Min Act: -0.1700
Data Index: 1949484 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.5886. Min Act: -0.1700
Data Index: 1199017 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.5886. Min Act: -0.1700
Data Index: 219287 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.5886. Min Act: -0.1700
Data Index: 1934000 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.5886. Min Act: -0.1700
Data Index: 8018690 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.5261. Min Act: -0.1700
Data Index: 5479324 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.5261. Min Act: -0.1700
Data Index: 2252266 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.5886. Min Act: -0.1700
Data Index: 7828917 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.4636. Min Act: -0.1700
Data Index: 5337030 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.4636. Min Act: -0.1700
Data Index: 3257645 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.4636. Min Act: -0.1700
Data Index: 2708963 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.4636. Min Act: -0.1700
Data Index: 6709035 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2136. Min Range: -8.2136
Max Act: 7.4636. Min Act: -0.1700
Data Index: 5290753 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19