Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 703 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.7541. Min Act: -0.1700
Data Index: 1351018 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.6916. Min Act: -0.1700
Data Index: 6284313 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.7228. Min Act: -0.1700
Data Index: 1036880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.6603. Min Act: -0.1700
Data Index: 5274525 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.6291. Min Act: -0.1700
Data Index: 8497516 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.6291. Min Act: -0.1700
Data Index: 2523528 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.6291. Min Act: -0.1700
Data Index: 1706970 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.6291. Min Act: -0.1700
Data Index: 4599654 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5978. Min Act: -0.1700
Data Index: 6888962 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5978. Min Act: -0.1700
Data Index: 6999874 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5978. Min Act: -0.1700
Data Index: 5682818 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5978. Min Act: -0.1690
Data Index: 1900297 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5978. Min Act: -0.1700
Data Index: 8818333 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5978. Min Act: -0.1700
Data Index: 902564 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5666. Min Act: -0.1700
Data Index: 189218 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5666. Min Act: -0.1700
Data Index: 5441629 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5353. Min Act: -0.1700
Data Index: 5562110 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5666. Min Act: -0.1700
Data Index: 2635583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5666. Min Act: -0.1700
Data Index: 6205271 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7541. Min Range: -4.7541
Max Act: 4.5353. Min Act: -0.1700
Data Index: 4318703 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19