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

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

Neuron 4401 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3975. Min Range: -4.3975

Max Act: 4.3975. Min Act: -0.0000

Data Index: 452158 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.6098. Min Act: -0.0000

Data Index: 208876 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 4.3975. Min Range: -4.3975

Max Act: 4.1939. Min Act: -0.0000

Data Index: 889672 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.5196. Min Act: -0.0000

Data Index: 132791 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.4071. Min Act: -0.0000

Data Index: 1247230 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.2369. Min Act: -0.0000

Data Index: 132728 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.4253. Min Act: -0.0000

Data Index: 1217650 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.4159. Min Act: -0.0000

Data Index: 805170 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.0847. Min Act: -0.0000

Data Index: 988691 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.0925. Min Act: -0.0000

Data Index: 515035 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 4.3975. Min Range: -4.3975

Max Act: 2.9932. Min Act: -0.0000

Data Index: 300954 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 4.3975. Min Range: -4.3975

Max Act: 2.9912. Min Act: -0.0000

Data Index: 1429141 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 4.3975. Min Range: -4.3975

Max Act: 2.9810. Min Act: -0.0000

Data Index: 1588558 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 4.3975. Min Range: -4.3975

Max Act: 2.9417. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 4.3975. Min Range: -4.3975

Max Act: 2.9156. Min Act: -0.0001

Data Index: 1499891 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.0495. Min Act: -0.0000

Data Index: 275189 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.1337. Min Act: -0.0000

Data Index: 1466247 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 4.3975. Min Range: -4.3975

Max Act: 2.9244. Min Act: -0.0000

Data Index: 703098 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 4.3975. Min Range: -4.3975

Max Act: 3.0414. Min Act: -0.0000

Data Index: 1340514 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 4.3975. Min Range: -4.3975

Max Act: 2.8478. Min Act: -0.0000

Data Index: 1539644 (Python Code)

Max Activating Token Index: 305