Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1069 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0614. Min Range: -5.0614
Max Act: 5.0614. Min Act: -0.1700
Data Index: 1258883 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.8426. Min Act: -0.1700
Data Index: 6335648 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.8426. Min Act: -0.1700
Data Index: 3725395 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.7489. Min Act: -0.1700
Data Index: 1073674 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.6239. Min Act: -0.1700
Data Index: 7268291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.6239. Min Act: -0.1700
Data Index: 5846032 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.6551. Min Act: -0.1700
Data Index: 8785260 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.6551. Min Act: -0.1700
Data Index: 6127870 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5926. Min Act: -0.1700
Data Index: 5562290 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.6239. Min Act: -0.1700
Data Index: 511674 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5926. Min Act: -0.1700
Data Index: 2903095 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5614. Min Act: -0.1700
Data Index: 1412497 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5614. Min Act: -0.1700
Data Index: 7377661 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5926. Min Act: -0.1700
Data Index: 96799 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5614. Min Act: -0.1700
Data Index: 5426535 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5301. Min Act: -0.1700
Data Index: 2029602 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5301. Min Act: -0.1700
Data Index: 5611239 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5301. Min Act: -0.1700
Data Index: 4789437 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.5301. Min Act: -0.1700
Data Index: 96800 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0614. Min Range: -5.0614
Max Act: 4.4989. Min Act: -0.1700
Data Index: 3070123 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19