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

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

Neuron 3368 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1559846 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1265619 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.3472. Min Act: -0.0000

Data Index: 481213 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.3349. Min Act: -0.0000

Data Index: 901196 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.3324. Min Act: -0.0000

Data Index: 10729 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.3393. Min Act: -0.0000

Data Index: 109907 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.3329. Min Act: -0.0000

Data Index: 656354 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2907. Min Act: -0.0000

Data Index: 194207 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.3108. Min Act: -0.0000

Data Index: 925022 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1213656 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2933. Min Act: -0.0000

Data Index: 716790 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1155110 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2952. Min Act: -0.0000

Data Index: 775273 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2942. Min Act: -0.0000

Data Index: 122267 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1272207 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1011074 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2953. Min Act: -0.0000

Data Index: 661051 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1582310 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2655. Min Act: -0.0000

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.4229. Min Range: -0.4229

Max Act: 0.2619. Min Act: -0.0000

Data Index: 613535 (C4 (Web Text))

Max Activating Token Index: 784