Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.2594. Min Act: -0.1700
Data Index: 8109401 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.2594. Min Act: -0.1700
Data Index: 5179228 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.2437. Min Act: -0.1700
Data Index: 1118666 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.2123. Min Act: -0.1700
Data Index: 6603858 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.2280. Min Act: -0.1700
Data Index: 3932042 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.2123. Min Act: -0.1700
Data Index: 558057 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1966. Min Act: -0.1700
Data Index: 5710668 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1966. Min Act: -0.1700
Data Index: 4430466 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1966. Min Act: -0.1700
Data Index: 2705434 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1966. Min Act: -0.1700
Data Index: 7904919 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1808. Min Act: -0.1700
Data Index: 4265918 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1179. Min Act: -0.1700
Data Index: 2756208 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1179. Min Act: -0.1700
Data Index: 8025609 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1336. Min Act: -0.1700
Data Index: 8626003 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1494. Min Act: -0.1700
Data Index: 2733004 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1021. Min Act: -0.1700
Data Index: 5849134 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1336. Min Act: -0.1700
Data Index: 4765925 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1021. Min Act: -0.1700
Data Index: 3101694 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.1021. Min Act: -0.1700
Data Index: 187435 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2594. Min Range: -3.2594
Max Act: 3.0863. Min Act: -0.1700
Data Index: 2602895 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19