Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3983 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7509. Min Act: -0.1700
Data Index: 6429163 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7196. Min Act: -0.1700
Data Index: 6432058 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7196. Min Act: -0.1700
Data Index: 4476704 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 503974 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 4350023 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 2378810 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 1762832 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 7577629 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 3189954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 8760797 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 4719204 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 7370796 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 3761275 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 4472710 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 8643104 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 3212117 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 6357380 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 3304456 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 1649556 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 6516356 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19