Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1295 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4582. Min Act: -0.0001

Data Index: 1321114 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4004. Min Act: -0.0001

Data Index: 938812 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4508. Min Act: -0.0001

Data Index: 325338 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4030. Min Act: -0.0001

Data Index: 428379 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4076. Min Act: -0.0001

Data Index: 971228 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3971. Min Act: -0.0001

Data Index: 651859 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3943. Min Act: -0.0001

Data Index: 352585 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3422. Min Act: -0.0001

Data Index: 891159 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3648. Min Act: -0.0001

Data Index: 374592 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3312. Min Act: -0.0001

Data Index: 451394 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3177. Min Act: -0.0001

Data Index: 699809 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3507. Min Act: -0.0001

Data Index: 316522 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1179973 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3327. Min Act: -0.0001

Data Index: 712644 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3682. Min Act: -0.0001

Data Index: 797511 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3206. Min Act: -0.0001

Data Index: 505761 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3658. Min Act: -0.0001

Data Index: 619455 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3166. Min Act: -0.0001

Data Index: 454621 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3132. Min Act: -0.0001

Data Index: 829194 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1257872 (C4 (Web Text))

Max Activating Token Index: 657