Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5224 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1176. Min Range: -6.1176
Max Act: 6.1176. Min Act: -0.1700
Data Index: 5705601 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1176. Min Range: -6.1176
Max Act: 6.0551. Min Act: -0.1700
Data Index: 2074980 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.9926. Min Act: -0.1700
Data Index: 4610220 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.9614. Min Act: -0.1700
Data Index: 147404 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.9614. Min Act: -0.1700
Data Index: 5705599 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8989. Min Act: -0.1700
Data Index: 4283246 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8989. Min Act: -0.1700
Data Index: 7752479 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8364. Min Act: -0.1700
Data Index: 1595185 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8051. Min Act: -0.1700
Data Index: 7427981 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8364. Min Act: -0.1700
Data Index: 2725875 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8364. Min Act: -0.1700
Data Index: 1700255 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8051. Min Act: -0.1700
Data Index: 6643313 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.8364. Min Act: -0.1700
Data Index: 328389 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.7739. Min Act: -0.1700
Data Index: 5166803 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.7739. Min Act: -0.1700
Data Index: 3880142 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.7739. Min Act: -0.1700
Data Index: 6543847 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.7739. Min Act: -0.1700
Data Index: 7564984 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.7739. Min Act: -0.1700
Data Index: 1085305 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.7739. Min Act: -0.1700
Data Index: 4571904 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1176. Min Range: -6.1176
Max Act: 5.7426. Min Act: -0.1700
Data Index: 4976388 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19