Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1078 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.9071. Min Act: -0.1700
Data Index: 6068229 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.8446. Min Act: -0.1700
Data Index: 4114762 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.7196. Min Act: -0.1700
Data Index: 837673 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.5946. Min Act: -0.1700
Data Index: 3695790 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.4071. Min Act: -0.1700
Data Index: 4116078 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.4071. Min Act: -0.1700
Data Index: 8585941 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.3446. Min Act: -0.1700
Data Index: 5182627 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.3446. Min Act: -0.1700
Data Index: 4095052 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.2821. Min Act: -0.1700
Data Index: 1619476 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.2821. Min Act: -0.1700
Data Index: 1588798 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.2821. Min Act: -0.1700
Data Index: 5925824 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.2196. Min Act: -0.1700
Data Index: 7107115 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.2821. Min Act: -0.1700
Data Index: 6308125 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.1571. Min Act: -0.1700
Data Index: 4713791 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.1571. Min Act: -0.1700
Data Index: 6641217 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.1571. Min Act: -0.1700
Data Index: 1390532 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.2196. Min Act: -0.1700
Data Index: 6610051 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.0946. Min Act: -0.1700
Data Index: 3547392 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.0946. Min Act: -0.1700
Data Index: 3598345 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9071. Min Range: -8.9071
Max Act: 8.0946. Min Act: -0.1700
Data Index: 2220500 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19