Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.8640. Min Act: -0.1696
Data Index: 6882127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.8015. Min Act: -0.1700
Data Index: 7472098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.8015. Min Act: -0.1700
Data Index: 1871676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.8015. Min Act: -0.1700
Data Index: 1111267 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6765. Min Act: -0.1700
Data Index: 7636013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6765. Min Act: -0.1700
Data Index: 6492953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6765. Min Act: -0.1673
Data Index: 904472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6140. Min Act: -0.1700
Data Index: 4702275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6140. Min Act: -0.1700
Data Index: 2778328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6140. Min Act: -0.1699
Data Index: 5863004 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.5515. Min Act: -0.1700
Data Index: 2419094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.4890. Min Act: -0.1693
Data Index: 618648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.4890. Min Act: -0.1700
Data Index: 7923222 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3640. Min Act: -0.1700
Data Index: 7181685 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.4265. Min Act: -0.1697
Data Index: 4374140 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3640. Min Act: -0.1700
Data Index: 4533572 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3640. Min Act: -0.1700
Data Index: 7635084 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3327. Min Act: -0.1700
Data Index: 8686429 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.2702. Min Act: -0.1697
Data Index: 2785659 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.2702. Min Act: -0.1700
Data Index: 3383253 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19