Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 121 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.1959. Min Act: -0.1699
Data Index: 870799 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.1647. Min Act: -0.1700
Data Index: 545352 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.0709. Min Act: -0.1700
Data Index: 210927 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.1334. Min Act: -0.1700
Data Index: 1155242 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.1334. Min Act: -0.1700
Data Index: 956650 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9772. Min Act: -0.1700
Data Index: 630043 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9459. Min Act: -0.1700
Data Index: 881134 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9772. Min Act: -0.1700
Data Index: 398321 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.0084. Min Act: -0.1700
Data Index: 578368 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.0709. Min Act: -0.1700
Data Index: 1312428 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.8834. Min Act: -0.1700
Data Index: 740391 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9772. Min Act: -0.1700
Data Index: 379044 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.8834. Min Act: -0.1700
Data Index: 594721 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9147. Min Act: -0.1700
Data Index: 1170119 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9772. Min Act: -0.1700
Data Index: 1223541 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9459. Min Act: -0.1700
Data Index: 4424 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1959. Min Range: -6.1959
Max Act: 6.0084. Min Act: -0.1700
Data Index: 1089981 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9459. Min Act: -0.1700
Data Index: 520585 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9147. Min Act: -0.1700
Data Index: 494863 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1959. Min Range: -6.1959
Max Act: 5.9772. Min Act: -0.1700
Data Index: 512758 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19