Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.4727. Min Act: -0.1700
Data Index: 650757 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.3790. Min Act: -0.1700
Data Index: 4923688 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.3790. Min Act: -0.1700
Data Index: 4744384 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.3165. Min Act: -0.1700
Data Index: 4905231 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.3477. Min Act: -0.1700
Data Index: 656740 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2852. Min Act: -0.1700
Data Index: 7934838 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2852. Min Act: -0.1700
Data Index: 7068469 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2852. Min Act: -0.1700
Data Index: 6915183 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2852. Min Act: -0.1700
Data Index: 7585824 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2227. Min Act: -0.1700
Data Index: 4889780 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.1915. Min Act: -0.1700
Data Index: 3870516 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2227. Min Act: -0.1700
Data Index: 2964005 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2227. Min Act: -0.1700
Data Index: 8436015 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2227. Min Act: -0.1700
Data Index: 5536740 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2227. Min Act: -0.1700
Data Index: 1477834 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.1602. Min Act: -0.1700
Data Index: 82032 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.1602. Min Act: -0.1700
Data Index: 2882968 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.1602. Min Act: -0.1700
Data Index: 7036485 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.2227. Min Act: -0.1700
Data Index: 1576627 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4727. Min Range: -5.4727
Max Act: 5.1915. Min Act: -0.1700
Data Index: 5004671 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19