Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 258 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.6281. Min Act: -0.1700
Data Index: 1323414 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.6281. Min Act: -0.1700
Data Index: 1256201 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.5314. Min Act: -0.1700
Data Index: 457989 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4990. Min Act: -0.1700
Data Index: 1287265 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4990. Min Act: -0.1700
Data Index: 772768 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4990. Min Act: -0.1700
Data Index: 1217355 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.5152. Min Act: -0.1700
Data Index: 885825 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4828. Min Act: -0.1700
Data Index: 501216 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4828. Min Act: -0.1699
Data Index: 1132533 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4666. Min Act: -0.1700
Data Index: 1089803 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4828. Min Act: -0.1700
Data Index: 518870 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4828. Min Act: -0.1700
Data Index: 166821 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4666. Min Act: -0.1700
Data Index: 656246 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4666. Min Act: -0.1700
Data Index: 1085467 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4666. Min Act: -0.1700
Data Index: 847963 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4666. Min Act: -0.1700
Data Index: 625326 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4666. Min Act: -0.1700
Data Index: 538218 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4504. Min Act: -0.1700
Data Index: 302431 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4504. Min Act: -0.1700
Data Index: 1113653 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6281. Min Range: -2.6281
Max Act: 2.4504. Min Act: -0.1698
Data Index: 106636 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19