Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1130 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.7367. Min Act: -0.1700
Data Index: 6026767 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.4242. Min Act: -0.1700
Data Index: 2895201 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.3617. Min Act: -0.1700
Data Index: 2774577 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.2367. Min Act: -0.1700
Data Index: 7932673 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.2367. Min Act: -0.1700
Data Index: 7344937 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.1742. Min Act: -0.1700
Data Index: 2699632 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.1742. Min Act: -0.1700
Data Index: 8684903 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7367. Min Range: -9.7367
Max Act: 9.1742. Min Act: -0.1700
Data Index: 7390079 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.9867. Min Act: -0.1700
Data Index: 6328618 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.9867. Min Act: -0.1700
Data Index: 5595360 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.9242. Min Act: -0.1700
Data Index: 730551 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.9242. Min Act: -0.1700
Data Index: 7624954 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.8617. Min Act: -0.1700
Data Index: 6855061 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.8617. Min Act: -0.1700
Data Index: 7537519 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.8617. Min Act: -0.1700
Data Index: 2464357 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.7992. Min Act: -0.1700
Data Index: 4539836 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.7367. Min Act: -0.1700
Data Index: 7868246 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.7992. Min Act: -0.1700
Data Index: 3406848 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.7367. Min Act: -0.1700
Data Index: 7929807 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7367. Min Range: -9.7367
Max Act: 8.7367. Min Act: -0.1700
Data Index: 265315 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19