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

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

Neuron 1302 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: 1.3479. Min Range: -1.3479

Max Act: 1.3479. Min Act: -0.0001

Data Index: 1173477 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.3479. Min Range: -1.3479

Max Act: 1.2069. Min Act: -0.0001

Data Index: 124202 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.3479. Min Range: -1.3479

Max Act: 1.2333. Min Act: -0.0001

Data Index: 448288 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.9081. Min Act: -0.0001

Data Index: 1326530 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8392. Min Act: -0.0001

Data Index: 656466 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8518. Min Act: -0.0001

Data Index: 305212 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8064. Min Act: -0.0001

Data Index: 274853 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7937. Min Act: -0.0001

Data Index: 120631 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8183. Min Act: -0.0001

Data Index: 76770 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8251. Min Act: -0.0001

Data Index: 1335242 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8252. Min Act: -0.0001

Data Index: 5623 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7919. Min Act: -0.0001

Data Index: 222532 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7859. Min Act: -0.0001

Data Index: 451490 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7784. Min Act: -0.0001

Data Index: 930564 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8324. Min Act: -0.0001

Data Index: 521842 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7960. Min Act: -0.0001

Data Index: 968561 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1033947 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.8098. Min Act: -0.0001

Data Index: 995192 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7244. Min Act: -0.0001

Data Index: 1110440 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.3479. Min Range: -1.3479

Max Act: 0.7432. Min Act: -0.0001

Data Index: 704092 (C4 (Web Text))

Max Activating Token Index: 415