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

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

Neuron 1385 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5773. Min Range: -1.5773

Max Act: 1.5773. Min Act: -0.0000

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.5773. Min Range: -1.5773

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1342023 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.5773. Min Range: -1.5773

Max Act: 1.1412. Min Act: -0.0000

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.5773. Min Range: -1.5773

Max Act: 1.0378. Min Act: -0.0000

Data Index: 44671 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.5773. Min Range: -1.5773

Max Act: 1.0127. Min Act: -0.0000

Data Index: 267400 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.5773. Min Range: -1.5773

Max Act: 1.0110. Min Act: -0.0000

Data Index: 472874 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.9790. Min Act: -0.0000

Data Index: 118100 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1190811 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.5773. Min Range: -1.5773

Max Act: 1.0278. Min Act: -0.0000

Data Index: 828879 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.9325. Min Act: -0.0000

Data Index: 209365 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8845. Min Act: -0.0000

Data Index: 392691 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1153267 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1291059 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1186503 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1067985 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1163761 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1013443 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8156. Min Act: -0.0000

Data Index: 853653 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8456. Min Act: -0.0000

Data Index: 836016 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.5773. Min Range: -1.5773

Max Act: 0.8349. Min Act: -0.0000

Data Index: 507264 (C4 (Web Text))

Max Activating Token Index: 290