Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4306 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1881. Min Act: -0.1700
Data Index: 6817716 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1881. Min Act: -0.1700
Data Index: 7919268 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1881. Min Act: -0.1700
Data Index: 7919297 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1569. Min Act: -0.1700
Data Index: 6628536 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1569. Min Act: -0.1700
Data Index: 6481154 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0943. Min Act: -0.1700
Data Index: 2164905 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1256. Min Act: -0.1700
Data Index: 8381366 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1256. Min Act: -0.1700
Data Index: 4327159 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0943. Min Act: -0.1700
Data Index: 1636118 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0943. Min Act: -0.1700
Data Index: 7059189 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.1256. Min Act: -0.1700
Data Index: 4863605 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 5293631 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 6465028 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 2897339 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 3462468 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 7268025 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 7286763 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 930855 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 5048316 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1881. Min Range: -4.1881
Max Act: 4.0631. Min Act: -0.1700
Data Index: 5109573 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19