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

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

Neuron 2394 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4201. Min Act: -0.0000

Data Index: 847671 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4480. Min Act: -0.0000

Data Index: 485458 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4288. Min Act: -0.0000

Data Index: 224828 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4268. Min Act: -0.0000

Data Index: 397353 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3992. Min Act: -0.0000

Data Index: 781001 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4132. Min Act: -0.0001

Data Index: 3121 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4214. Min Act: -0.0000

Data Index: 805192 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3352. Min Act: -0.0000

Data Index: 393143 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3380. Min Act: -0.0000

Data Index: 537358 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1022705 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3786. Min Act: -0.0000

Data Index: 658462 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3440. Min Act: -0.0000

Data Index: 251075 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1208334 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1325555 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3569. Min Act: -0.0000

Data Index: 814774 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3636. Min Act: -0.0000

Data Index: 945178 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3326. Min Act: -0.0001

Data Index: 533785 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1094295 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3521. Min Act: -0.0000

Data Index: 116492 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3280. Min Act: -0.0000

Data Index: 35218 (C4 (Web Text))

Max Activating Token Index: 786