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

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

Neuron 3444 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: 1.9445. Min Range: -1.9445

Max Act: 1.8856. Min Act: -0.0000

Data Index: 703753 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8949. Min Act: -0.0000

Data Index: 1356848 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.9445. Min Act: -0.0001

Data Index: 943108 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8048. Min Act: -0.0001

Data Index: 67030 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8335. Min Act: -0.0001

Data Index: 416843 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7775. Min Act: -0.0000

Data Index: 1140792 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7268. Min Act: -0.0001

Data Index: 202590 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7670. Min Act: -0.0001

Data Index: 816528 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8742. Min Act: -0.0000

Data Index: 154026 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8146. Min Act: -0.0000

Data Index: 1006656 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8603. Min Act: -0.0000

Data Index: 61148 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.6055. Min Act: -0.0000

Data Index: 32337 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7493. Min Act: -0.0001

Data Index: 779198 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7877. Min Act: -0.0001

Data Index: 1126905 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7972. Min Act: -0.0000

Data Index: 335823 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7811. Min Act: -0.0000

Data Index: 79266 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8257. Min Act: -0.0001

Data Index: 447747 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8199. Min Act: -0.0001

Data Index: 687959 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7706. Min Act: -0.0000

Data Index: 565231 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.8176. Min Act: -0.0000

Data Index: 560828 (C4 (Web Text))

Max Activating Token Index: 469