Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.2058. Min Act: -0.1700
Data Index: 4611641 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.1433. Min Act: -0.1700
Data Index: 335790 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.1433. Min Act: -0.1700
Data Index: 6655224 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.1121. Min Act: -0.1700
Data Index: 2261357 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.0496. Min Act: -0.1700
Data Index: 3757957 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.0808. Min Act: -0.1700
Data Index: 1069734 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.0496. Min Act: -0.1700
Data Index: 4010287 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2058. Min Range: -6.2058
Max Act: 6.0183. Min Act: -0.1700
Data Index: 418082 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.9871. Min Act: -0.1700
Data Index: 1612024 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.9558. Min Act: -0.1700
Data Index: 4546404 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.9558. Min Act: -0.1700
Data Index: 1624750 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.8933. Min Act: -0.1700
Data Index: 5268347 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.9246. Min Act: -0.1700
Data Index: 2849677 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.9246. Min Act: -0.1700
Data Index: 4536058 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.8621. Min Act: -0.1700
Data Index: 8080926 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.8933. Min Act: -0.1700
Data Index: 6134045 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.8621. Min Act: -0.1700
Data Index: 1525771 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.8621. Min Act: -0.1700
Data Index: 1422405 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.8308. Min Act: -0.1700
Data Index: 522237 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2058. Min Range: -6.2058
Max Act: 5.8308. Min Act: -0.1700
Data Index: 138815 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19