Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.9219. Min Act: -0.1700
Data Index: 445859 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.6094. Min Act: -0.1700
Data Index: 4211242 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.5156. Min Act: -0.1700
Data Index: 1259844 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.5469. Min Act: -0.1700
Data Index: 2162685 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.4844. Min Act: -0.1700
Data Index: 3338865 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.5156. Min Act: -0.1700
Data Index: 7806687 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.4531. Min Act: -0.1700
Data Index: 2353133 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.4844. Min Act: -0.1700
Data Index: 1989008 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.4844. Min Act: -0.1700
Data Index: 5559133 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.4531. Min Act: -0.1700
Data Index: 950012 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.4219. Min Act: -0.1700
Data Index: 3213349 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.4219. Min Act: -0.1700
Data Index: 4660957 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3906. Min Act: -0.1700
Data Index: 852395 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3594. Min Act: -0.1700
Data Index: 6834638 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3594. Min Act: -0.1700
Data Index: 1341640 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3594. Min Act: -0.1700
Data Index: 7087421 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3594. Min Act: -0.1700
Data Index: 7218871 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3281. Min Act: -0.1700
Data Index: 5526729 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3281. Min Act: -0.1700
Data Index: 4014592 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9219. Min Range: -4.9219
Max Act: 4.3281. Min Act: -0.1700
Data Index: 7018668 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19