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

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

Neuron 2596 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: 0.8132. Min Range: -0.8132

Max Act: 0.8132. Min Act: -0.0001

Data Index: 636102 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.8076. Min Act: -0.0001

Data Index: 873689 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7163. Min Act: -0.0001

Data Index: 491572 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7307. Min Act: -0.0001

Data Index: 1178444 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7456. Min Act: -0.0001

Data Index: 220407 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7403. Min Act: -0.0001

Data Index: 685719 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7139. Min Act: -0.0001

Data Index: 230307 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7208. Min Act: -0.0001

Data Index: 461875 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6517. Min Act: -0.0001

Data Index: 409614 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6859. Min Act: -0.0001

Data Index: 810455 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7039. Min Act: -0.0001

Data Index: 819925 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6626. Min Act: -0.0001

Data Index: 816637 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6304. Min Act: -0.0001

Data Index: 447845 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6960. Min Act: -0.0001

Data Index: 570205 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6533. Min Act: -0.0001

Data Index: 716719 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6487. Min Act: -0.0001

Data Index: 360154 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6677. Min Act: -0.0001

Data Index: 1185859 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6706. Min Act: -0.0001

Data Index: 601585 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6453. Min Act: -0.0001

Data Index: 666238 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1016374 (C4 (Web Text))

Max Activating Token Index: 963