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

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

Neuron 1122 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: 3.0189. Min Range: -3.0189

Max Act: 2.8339. Min Act: -0.0001

Data Index: 631938 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 3.0189. Min Range: -3.0189

Max Act: 3.0189. Min Act: -0.0001

Data Index: 1337464 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3335. Min Act: -0.0001

Data Index: 731919 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3049. Min Act: -0.0001

Data Index: 553809 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2909. Min Act: -0.0001

Data Index: 171311 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3934. Min Act: -0.0001

Data Index: 1203487 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2480. Min Act: -0.0001

Data Index: 285747 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3479. Min Act: -0.0001

Data Index: 352275 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3357. Min Act: -0.0001

Data Index: 1229875 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3151. Min Act: -0.0001

Data Index: 1150237 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 3.0189. Min Range: -3.0189

Max Act: 1.9301. Min Act: -0.0001

Data Index: 149696 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 3.0189. Min Range: -3.0189

Max Act: 1.9105. Min Act: -0.0001

Data Index: 949295 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.1947. Min Act: -0.0001

Data Index: 4507 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2108. Min Act: -0.0001

Data Index: 1200365 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.1080. Min Act: -0.0001

Data Index: 88406 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.0369. Min Act: -0.0001

Data Index: 1022342 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.1238. Min Act: -0.0001

Data Index: 622262 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3070. Min Act: -0.0001

Data Index: 1100258 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.0277. Min Act: -0.0001

Data Index: 1244472 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2238. Min Act: -0.0001

Data Index: 1203520 (C4 (Web Text))

Max Activating Token Index: 26