Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2484. Min Range: -4.2484
Max Act: 4.2484. Min Act: -0.1700
Data Index: 1792496 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2484. Min Range: -4.2484
Max Act: 4.1234. Min Act: -0.1700
Data Index: 4985236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2484. Min Range: -4.2484
Max Act: 4.0921. Min Act: -0.1700
Data Index: 994287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2484. Min Range: -4.2484
Max Act: 4.0296. Min Act: -0.1700
Data Index: 338582 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2484. Min Range: -4.2484
Max Act: 4.0296. Min Act: -0.1700
Data Index: 5626620 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2484. Min Range: -4.2484
Max Act: 4.0296. Min Act: -0.1700
Data Index: 4655280 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9983. Min Act: -0.1700
Data Index: 3797610 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9983. Min Act: -0.1700
Data Index: 1803993 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9983. Min Act: -0.1700
Data Index: 1714090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9983. Min Act: -0.1700
Data Index: 5275340 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9983. Min Act: -0.1700
Data Index: 1283349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9983. Min Act: -0.1700
Data Index: 3018050 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9983. Min Act: -0.1700
Data Index: 3496388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9671. Min Act: -0.1700
Data Index: 2602675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9671. Min Act: -0.1700
Data Index: 1992860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9671. Min Act: -0.1700
Data Index: 2927571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9671. Min Act: -0.1700
Data Index: 517184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9671. Min Act: -0.1700
Data Index: 35505 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9671. Min Act: -0.1700
Data Index: 6371352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2484. Min Range: -4.2484
Max Act: 3.9671. Min Act: -0.1700
Data Index: 871079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19