Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1180 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.2248. Min Act: -0.0001

Data Index: 889290 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.0816. Min Act: -0.0001

Data Index: 885814 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.6448. Min Act: -0.0001

Data Index: 238466 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.8683. Min Act: -0.0001

Data Index: 1320096 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.5004. Min Act: -0.0001

Data Index: 649493 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.8103. Min Act: -0.0001

Data Index: 1327798 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.4403. Min Act: -0.0001

Data Index: 92260 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.6812. Min Act: -0.0001

Data Index: 1297280 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.6918. Min Act: -0.0001

Data Index: 60907 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.4202. Min Act: -0.0001

Data Index: 1150254 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.3121. Min Act: -0.0001

Data Index: 1118165 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.2733. Min Act: -0.0001

Data Index: 161835 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.0784. Min Act: -0.0001

Data Index: 538588 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.5749. Min Act: -0.0001

Data Index: 943568 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.6814. Min Act: -0.0001

Data Index: 893935 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.3823. Min Act: -0.0001

Data Index: 149009 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.5166. Min Act: -0.0001

Data Index: 499541 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.5408. Min Act: -0.0001

Data Index: 485247 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.5235. Min Act: -0.0001

Data Index: 962158 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.6448. Min Range: -3.6448

Max Act: 2.3869. Min Act: -0.0001

Data Index: 818423 (C4 (Web Text))

Max Activating Token Index: 793