Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3396 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1203. Min Range: -2.1203

Max Act: 2.0963. Min Act: -0.0000

Data Index: 690956 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 2.1203. Min Range: -2.1203

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1113409 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.9211. Min Act: -0.0001

Data Index: 651369 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.7785. Min Act: -0.0000

Data Index: 266803 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.8279. Min Act: -0.0001

Data Index: 1038862 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.7805. Min Act: -0.0000

Data Index: 94346 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.7050. Min Act: -0.0000

Data Index: 505311 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.6271. Min Act: -0.0000

Data Index: 220858 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.5857. Min Act: -0.0000

Data Index: 943011 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.5166. Min Act: -0.0000

Data Index: 394571 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.4870. Min Act: -0.0000

Data Index: 620985 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1204937 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.4582. Min Act: -0.0000

Data Index: 430631 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.4074. Min Act: -0.0000

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.3450. Min Act: -0.0000

Data Index: 993753 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.3563. Min Act: -0.0000

Data Index: 661414 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.4006. Min Act: -0.0000

Data Index: 1012048 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.3819. Min Act: -0.0000

Data Index: 286985 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1342551 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 2.1203. Min Range: -2.1203

Max Act: 1.3333. Min Act: -0.0000

Data Index: 764583 (C4 (Web Text))

Max Activating Token Index: 188