Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1901 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.1858. Min Act: -0.1700
Data Index: 8084032 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.1141. Min Act: -0.1700
Data Index: 6772066 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0681. Min Act: -0.1700
Data Index: 6676509 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0796. Min Act: -0.1700
Data Index: 5289012 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0556. Min Act: -0.1700
Data Index: 680567 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0572. Min Act: -0.1700
Data Index: 5390255 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0573. Min Act: -0.1700
Data Index: 2100951 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0532. Min Act: -0.1700
Data Index: 5498715 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0392. Min Act: -0.1700
Data Index: 3319833 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0320. Min Act: -0.1700
Data Index: 6275859 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0084. Min Act: -0.1700
Data Index: 8150201 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0658. Min Act: -0.1700
Data Index: 6288825 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0131. Min Act: -0.1700
Data Index: 380735 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0312. Min Act: -0.1700
Data Index: 7856704 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.1858. Min Range: -3.1858
Max Act: 3.0023. Min Act: -0.1700
Data Index: 2260330 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.1858. Min Range: -3.1858
Max Act: 2.9965. Min Act: -0.1700
Data Index: 4379324 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.1858. Min Range: -3.1858
Max Act: 2.9598. Min Act: -0.1700
Data Index: 4590516 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.1858. Min Range: -3.1858
Max Act: 2.9878. Min Act: -0.1700
Data Index: 3072811 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.1858. Min Range: -3.1858
Max Act: 2.9680. Min Act: -0.1700
Data Index: 7024279 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.1858. Min Range: -3.1858
Max Act: 2.9720. Min Act: -0.1700
Data Index: 4850123 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full textTruncated
Full Text #19