Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.0303. Min Range: -4.0303
Max Act: 4.0303. Min Act: -0.1700
Data Index: 8259329 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.9954. Min Act: -0.1700
Data Index: 401252 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.9392. Min Act: -0.1700
Data Index: 6523852 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.9349. Min Act: -0.1700
Data Index: 6142260 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.9089. Min Act: -0.1700
Data Index: 2763317 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8682. Min Act: -0.1700
Data Index: 6863759 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8841. Min Act: -0.1700
Data Index: 3996570 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8743. Min Act: -0.1700
Data Index: 2546973 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8551. Min Act: -0.1700
Data Index: 5965196 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8713. Min Act: -0.1700
Data Index: 2398644 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8542. Min Act: -0.1700
Data Index: 4470227 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8189. Min Act: -0.1700
Data Index: 5145390 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8295. Min Act: -0.1700
Data Index: 8357373 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8361. Min Act: -0.1700
Data Index: 8223689 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8336. Min Act: -0.1700
Data Index: 1927789 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8282. Min Act: -0.1700
Data Index: 7262050 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8558. Min Act: -0.1700
Data Index: 1007973 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8132. Min Act: -0.1700
Data Index: 3584382 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8125. Min Act: -0.1700
Data Index: 6044902 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 4.0303. Min Range: -4.0303
Max Act: 3.8047. Min Act: -0.1700
Data Index: 6147637 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full textTruncated
Full Text #19