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

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

Neuron 3775 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: 0.4489. Min Range: -0.4489

Max Act: 0.4489. Min Act: -0.0000

Data Index: 390506 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4064. Min Act: -0.0000

Data Index: 10150 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.3652. Min Act: -0.0001

Data Index: 680560 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.3677. Min Act: -0.0001

Data Index: 480774 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.3360. Min Act: -0.0000

Data Index: 336524 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.3403. Min Act: -0.0000

Data Index: 843869 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.3153. Min Act: -0.0001

Data Index: 166762 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2910. Min Act: -0.0000

Data Index: 844718 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2597. Min Act: -0.0001

Data Index: 553354 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2930. Min Act: -0.0001

Data Index: 704458 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1148112 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2496. Min Act: -0.0000

Data Index: 812672 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2489. Min Act: -0.0000

Data Index: 128376 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2235. Min Act: -0.0001

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2070. Min Act: -0.0000

Data Index: 492143 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2285. Min Act: -0.0001

Data Index: 482416 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2314. Min Act: -0.0000

Data Index: 126919 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2305. Min Act: -0.0000

Data Index: 21755 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2301. Min Act: -0.0000

Data Index: 131088 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.2243. Min Act: -0.0000

Data Index: 900733 (C4 (Web Text))

Max Activating Token Index: 855