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

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

Neuron 4058 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3523. Min Range: -3.3523

Max Act: 3.3523. Min Act: -0.0000

Data Index: 286020 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 3.3523. Min Range: -3.3523

Max Act: 2.8867. Min Act: -0.0000

Data Index: 18247 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 3.3523. Min Range: -3.3523

Max Act: 2.5386. Min Act: -0.0000

Data Index: 387712 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.3523. Min Range: -3.3523

Max Act: 2.1039. Min Act: -0.0000

Data Index: 113381 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 3.3523. Min Range: -3.3523

Max Act: 2.1071. Min Act: -0.0000

Data Index: 175958 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 3.3523. Min Range: -3.3523

Max Act: 2.0392. Min Act: -0.0000

Data Index: 219750 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 3.3523. Min Range: -3.3523

Max Act: 2.2209. Min Act: -0.0000

Data Index: 975380 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 3.3523. Min Range: -3.3523

Max Act: 2.0708. Min Act: -0.0000

Data Index: 597991 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1357470 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.8352. Min Act: -0.0000

Data Index: 620000 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.9184. Min Act: -0.0000

Data Index: 696536 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.8395. Min Act: -0.0000

Data Index: 473797 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.8257. Min Act: -0.0000

Data Index: 672413 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.8186. Min Act: -0.0000

Data Index: 960407 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.8091. Min Act: -0.0000

Data Index: 195259 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.7523. Min Act: -0.0000

Data Index: 134077 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.8534. Min Act: -0.0000

Data Index: 239648 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.6349. Min Act: -0.0000

Data Index: 538985 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.6850. Min Act: -0.0000

Data Index: 919912 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 3.3523. Min Range: -3.3523

Max Act: 1.6575. Min Act: -0.0000

Data Index: 103778 (C4 (Web Text))

Max Activating Token Index: 651