Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1605 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.6514. Min Act: -0.1700
Data Index: 321905 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.6193. Min Act: -0.1700
Data Index: 86818 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5871. Min Act: -0.1700
Data Index: 630533 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.6032. Min Act: -0.1700
Data Index: 856426 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5710. Min Act: -0.1700
Data Index: 1186430 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5548. Min Act: -0.1700
Data Index: 1242612 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 927165 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5548. Min Act: -0.1700
Data Index: 943895 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 1131943 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 1333621 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5548. Min Act: -0.1700
Data Index: 723160 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5548. Min Act: -0.1700
Data Index: 1319466 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5548. Min Act: -0.1700
Data Index: 602461 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 248941 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 888012 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 309020 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 938397 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 229415 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5387. Min Act: -0.1700
Data Index: 943554 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6514. Min Range: -2.6514
Max Act: 2.5225. Min Act: -0.1700
Data Index: 352118 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19