Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4011 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.5212. Min Act: -0.0001

Data Index: 973583 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.4282. Min Act: -0.0001

Data Index: 35050 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.4577. Min Act: -0.0001

Data Index: 694295 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.3409. Min Act: -0.0001

Data Index: 1086710 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2201. Min Act: -0.0001

Data Index: 89184 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2032. Min Act: -0.0001

Data Index: 173090 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1455. Min Act: -0.0001

Data Index: 883259 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1951. Min Act: -0.0001

Data Index: 350043 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1183. Min Act: -0.0000

Data Index: 697161 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2326. Min Act: -0.0001

Data Index: 1144958 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0864. Min Act: -0.0001

Data Index: 128985 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1812. Min Act: -0.0001

Data Index: 522378 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0766. Min Act: -0.0001

Data Index: 490092 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0964. Min Act: -0.0001

Data Index: 893214 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1354. Min Act: -0.0001

Data Index: 905493 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0231. Min Act: -0.0001

Data Index: 124886 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0490. Min Act: -0.0001

Data Index: 110776 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0020. Min Act: -0.0001

Data Index: 728716 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 1.5212. Min Range: -1.5212

Max Act: 0.9974. Min Act: -0.0001

Data Index: 107989 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0233. Min Act: -0.0001

Data Index: 1194278 (C4 (Web Text))

Max Activating Token Index: 45