Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1438. Min Range: -4.1438
Max Act: 4.1438. Min Act: -0.1700
Data Index: 3577528 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1438. Min Range: -4.1438
Max Act: 4.0813. Min Act: -0.1700
Data Index: 7870361 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1438. Min Range: -4.1438
Max Act: 4.0813. Min Act: -0.1700
Data Index: 1224202 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1438. Min Range: -4.1438
Max Act: 4.0813. Min Act: -0.1700
Data Index: 1166535 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1438. Min Range: -4.1438
Max Act: 4.0500. Min Act: -0.1700
Data Index: 2494045 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1438. Min Range: -4.1438
Max Act: 4.0188. Min Act: -0.1700
Data Index: 6133468 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9563. Min Act: -0.1700
Data Index: 4648025 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9875. Min Act: -0.1700
Data Index: 6058808 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9875. Min Act: -0.1700
Data Index: 2510840 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9875. Min Act: -0.1700
Data Index: 6427647 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9875. Min Act: -0.1700
Data Index: 3245743 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9563. Min Act: -0.1700
Data Index: 2648489 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9563. Min Act: -0.1700
Data Index: 2406990 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9563. Min Act: -0.1700
Data Index: 6964946 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9563. Min Act: -0.1700
Data Index: 2001403 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.8937. Min Act: -0.1700
Data Index: 2349279 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9250. Min Act: -0.1700
Data Index: 5438935 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.9250. Min Act: -0.1700
Data Index: 5933324 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.8937. Min Act: -0.1700
Data Index: 2999483 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1438. Min Range: -4.1438
Max Act: 3.8937. Min Act: -0.1700
Data Index: 3955351 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19