Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 962 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.9016. Min Act: -0.1700
Data Index: 699907 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.7297. Min Act: -0.1700
Data Index: 1243491 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.5891. Min Act: -0.1700
Data Index: 467804 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.5578. Min Act: -0.1700
Data Index: 737791 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.5891. Min Act: -0.1700
Data Index: 398548 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.5578. Min Act: -0.1700
Data Index: 1143480 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.4797. Min Act: -0.1700
Data Index: 1028398 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.4484. Min Act: -0.1700
Data Index: 1245487 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.3859. Min Act: -0.1700
Data Index: 931533 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.3547. Min Act: -0.1700
Data Index: 1135870 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.2766. Min Act: -0.1700
Data Index: 1392654 (Python Code)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.4016. Min Act: -0.1700
Data Index: 172440 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.2141. Min Act: -0.1700
Data Index: 891133 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.3703. Min Act: -0.1700
Data Index: 411727 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.3234. Min Act: -0.1700
Data Index: 461700 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.2141. Min Act: -0.1700
Data Index: 421312 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.2297. Min Act: -0.1698
Data Index: 303603 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.1828. Min Act: -0.1700
Data Index: 536407 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.1672. Min Act: -0.1700
Data Index: 387128 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9016. Min Range: -6.9016
Max Act: 6.2141. Min Act: -0.1700
Data Index: 317285 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19