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

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

Neuron 3914 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3039. Min Range: -3.3039

Max Act: 3.3039. Min Act: -0.0000

Data Index: 1379232 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 3.3039. Min Range: -3.3039

Max Act: 3.0247. Min Act: -0.0000

Data Index: 122217 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.5989. Min Act: -0.0000

Data Index: 1331306 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.6655. Min Act: -0.0000

Data Index: 581672 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.6277. Min Act: -0.0000

Data Index: 835724 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.7407. Min Act: -0.0000

Data Index: 393644 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.6240. Min Act: -0.0000

Data Index: 1316276 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.4740. Min Act: -0.0000

Data Index: 849538 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.4369. Min Act: -0.0000

Data Index: 260430 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.6440. Min Act: -0.0000

Data Index: 419517 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.4644. Min Act: -0.0000

Data Index: 1150230 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.3067. Min Act: -0.0000

Data Index: 818881 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.3961. Min Act: -0.0000

Data Index: 4159 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.3913. Min Act: -0.0000

Data Index: 845093 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.5079. Min Act: -0.0000

Data Index: 549926 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.3326. Min Act: -0.0000

Data Index: 854042 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.3323. Min Act: -0.0000

Data Index: 128841 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.1872. Min Act: -0.0000

Data Index: 567842 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.1627. Min Act: -0.0000

Data Index: 1567460 (Python Code)

Max Activating Token Index: 257

Text #19

Max Range: 3.3039. Min Range: -3.3039

Max Act: 2.2771. Min Act: -0.0000

Data Index: 1227771 (C4 (Web Text))

Max Activating Token Index: 504