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

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

Neuron 3082 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: 2.4241. Min Range: -2.4241

Max Act: 2.4241. Min Act: -0.0000

Data Index: 821087 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.3596. Min Act: -0.0000

Data Index: 889499 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.3348. Min Act: -0.0000

Data Index: 1019949 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.1146. Min Act: -0.0000

Data Index: 778308 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.0581. Min Act: -0.0000

Data Index: 558056 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.0401. Min Act: -0.0000

Data Index: 1274869 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.0368. Min Act: -0.0000

Data Index: 574804 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.9176. Min Act: -0.0000

Data Index: 204008 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.9966. Min Act: -0.0000

Data Index: 316287 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.8337. Min Act: -0.0000

Data Index: 79435 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.9133. Min Act: -0.0000

Data Index: 187184 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1312802 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.7780. Min Act: -0.0000

Data Index: 1048336 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.9660. Min Act: -0.0000

Data Index: 840386 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.9320. Min Act: -0.0000

Data Index: 1334720 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.6954. Min Act: -0.0000

Data Index: 78597 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.7042. Min Act: -0.0000

Data Index: 600587 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.7734. Min Act: -0.0000

Data Index: 947089 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.7585. Min Act: -0.0000

Data Index: 181433 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 2.4241. Min Range: -2.4241

Max Act: 1.5380. Min Act: -0.0000

Data Index: 1031480 (C4 (Web Text))

Max Activating Token Index: 290