Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2190 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.2564. Min Range: -6.2564
Max Act: 6.2564. Min Act: -0.1700
Data Index: 4817982 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 6.2564. Min Range: -6.2564
Max Act: 6.2254. Min Act: -0.1700
Data Index: 6607018 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 6.2564. Min Range: -6.2564
Max Act: 6.1032. Min Act: -0.1700
Data Index: 8181707 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 6.2564. Min Range: -6.2564
Max Act: 6.0138. Min Act: -0.1700
Data Index: 1611890 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 6.2564. Min Range: -6.2564
Max Act: 6.0563. Min Act: -0.1700
Data Index: 7737781 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.9692. Min Act: -0.1700
Data Index: 6453111 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8928. Min Act: -0.1700
Data Index: 950819 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8703. Min Act: -0.1700
Data Index: 1822387 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8898. Min Act: -0.1700
Data Index: 2737018 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8497. Min Act: -0.1700
Data Index: 4173572 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8282. Min Act: -0.1700
Data Index: 1209795 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8464. Min Act: -0.1700
Data Index: 5435357 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8321. Min Act: -0.1700
Data Index: 4478731 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8496. Min Act: -0.1700
Data Index: 2332726 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8226. Min Act: -0.1700
Data Index: 3440637 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.7699. Min Act: -0.1700
Data Index: 6295480 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8327. Min Act: -0.1700
Data Index: 4270141 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8364. Min Act: -0.1700
Data Index: 3729213 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8391. Min Act: -0.1700
Data Index: 92438 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 6.2564. Min Range: -6.2564
Max Act: 5.8171. Min Act: -0.1700
Data Index: 4344902 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full textTruncated
Full Text #19