Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0421. Min Range: -6.0421
Max Act: 6.0421. Min Act: -0.1700
Data Index: 2801474 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.8858. Min Act: -0.1700
Data Index: 1882142 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.8858. Min Act: -0.1700
Data Index: 8351719 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.8546. Min Act: -0.1700
Data Index: 1782647 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.8858. Min Act: -0.1700
Data Index: 5068988 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.7608. Min Act: -0.1700
Data Index: 5754150 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.6983. Min Act: -0.1700
Data Index: 6850605 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.7296. Min Act: -0.1700
Data Index: 669366 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.6983. Min Act: -0.1700
Data Index: 8172194 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.6671. Min Act: -0.1700
Data Index: 1954945 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.6671. Min Act: -0.1700
Data Index: 2489048 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.6046. Min Act: -0.1700
Data Index: 6719637 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.6046. Min Act: -0.1700
Data Index: 5713175 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.5733. Min Act: -0.1700
Data Index: 7512504 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.5733. Min Act: -0.1700
Data Index: 6989640 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.5733. Min Act: -0.1700
Data Index: 3188953 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.5733. Min Act: -0.1700
Data Index: 3489686 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.5733. Min Act: -0.1700
Data Index: 4083954 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.5733. Min Act: -0.1700
Data Index: 3667954 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0421. Min Range: -6.0421
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1179564 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19