Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.8966. Min Act: -0.1700
Data Index: 2276259 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.8341. Min Act: -0.1700
Data Index: 8594094 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.7091. Min Act: -0.1700
Data Index: 4654156 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.6466. Min Act: -0.1700
Data Index: 1686113 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.5841. Min Act: -0.1700
Data Index: 1931708 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.5216. Min Act: -0.1700
Data Index: 6057561 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.5216. Min Act: -0.1700
Data Index: 3219293 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.4591. Min Act: -0.1700
Data Index: 5626049 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.4591. Min Act: -0.1700
Data Index: 5128628 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.3966. Min Act: -0.1700
Data Index: 2518318 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.3341. Min Act: -0.1700
Data Index: 383323 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.3341. Min Act: -0.1700
Data Index: 4773792 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.2716. Min Act: -0.1700
Data Index: 3474678 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.3341. Min Act: -0.1700
Data Index: 4225488 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.2716. Min Act: -0.1700
Data Index: 8068397 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.1466. Min Act: -0.1700
Data Index: 2536363 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.1466. Min Act: -0.1700
Data Index: 743357 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.1466. Min Act: -0.1700
Data Index: 1267373 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.0841. Min Act: -0.1700
Data Index: 792005 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8966. Min Range: -12.8966
Max Act: 12.0841. Min Act: -0.1700
Data Index: 4352549 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19