Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5212 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2661. Min Range: -4.2661
Max Act: 4.2661. Min Act: -0.1700
Data Index: 8551115 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2661. Min Range: -4.2661
Max Act: 4.1099. Min Act: -0.1700
Data Index: 2729957 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2661. Min Range: -4.2661
Max Act: 4.0786. Min Act: -0.1700
Data Index: 2717942 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2661. Min Range: -4.2661
Max Act: 4.0473. Min Act: -0.1700
Data Index: 7851815 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.9848. Min Act: -0.1700
Data Index: 6178236 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.9223. Min Act: -0.1700
Data Index: 2390007 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.9223. Min Act: -0.1700
Data Index: 6113070 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.9223. Min Act: -0.1700
Data Index: 7601631 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.8598. Min Act: -0.1700
Data Index: 3171829 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.8598. Min Act: -0.1700
Data Index: 7241935 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.8598. Min Act: -0.1700
Data Index: 5492767 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.8285. Min Act: -0.1700
Data Index: 5534158 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.8598. Min Act: -0.1700
Data Index: 3636189 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.8285. Min Act: -0.1700
Data Index: 3636188 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.7972. Min Act: -0.1700
Data Index: 6525436 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.7659. Min Act: -0.1700
Data Index: 2390012 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.7972. Min Act: -0.1700
Data Index: 11630 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.7972. Min Act: -0.1700
Data Index: 5534182 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.7972. Min Act: -0.1700
Data Index: 1205335 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2661. Min Range: -4.2661
Max Act: 3.7659. Min Act: -0.1700
Data Index: 7567192 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19