Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2784. Min Range: -7.2784
Max Act: 7.2784. Min Act: -0.1700
Data Index: 2696901 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.9034. Min Act: -0.1700
Data Index: 4504273 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.6534. Min Act: -0.1700
Data Index: 3193697 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.5909. Min Act: -0.1700
Data Index: 2883106 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.5596. Min Act: -0.1700
Data Index: 7861485 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.5284. Min Act: -0.1700
Data Index: 4349226 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.5284. Min Act: -0.1700
Data Index: 5420931 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.5284. Min Act: -0.1700
Data Index: 1636149 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4971. Min Act: -0.1700
Data Index: 6550355 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 4569137 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 8267049 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 4636454 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 1625516 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 3425614 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4346. Min Act: -0.1700
Data Index: 7018796 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4034. Min Act: -0.1700
Data Index: 5346267 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4034. Min Act: -0.1700
Data Index: 103462 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.4346. Min Act: -0.1700
Data Index: 7303317 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.3721. Min Act: -0.1700
Data Index: 2449268 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2784. Min Range: -7.2784
Max Act: 6.3721. Min Act: -0.1700
Data Index: 7425622 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19