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

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

Neuron 3775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4708. Min Range: -6.4708

Max Act: 6.3335. Min Act: -0.0000

Data Index: 989701 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 6.4708. Min Range: -6.4708

Max Act: 6.4708. Min Act: -0.0000

Data Index: 1036943 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 6.4708. Min Range: -6.4708

Max Act: 6.3791. Min Act: -0.0000

Data Index: 919095 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.7678. Min Act: -0.0000

Data Index: 326804 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.9866. Min Act: -0.0000

Data Index: 540144 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.8014. Min Act: -0.0000

Data Index: 470145 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.5666. Min Act: -0.0000

Data Index: 412350 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.5745. Min Act: -0.0000

Data Index: 579237 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.4803. Min Act: -0.0000

Data Index: 1029523 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.2952. Min Act: 0.0000

Data Index: 850403 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.6446. Min Act: -0.0000

Data Index: 211622 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.6234. Min Act: -0.0000

Data Index: 358196 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.2443. Min Act: -0.0000

Data Index: 136594 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.4003. Min Act: -0.0000

Data Index: 357990 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.3216. Min Act: -0.0000

Data Index: 360614 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 6.4708. Min Range: -6.4708

Max Act: 4.9076. Min Act: -0.0000

Data Index: 466185 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.0014. Min Act: -0.0000

Data Index: 1097023 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 6.4708. Min Range: -6.4708

Max Act: 4.9325. Min Act: -0.0000

Data Index: 1157646 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 6.4708. Min Range: -6.4708

Max Act: 4.7524. Min Act: 0.0001

Data Index: 83671 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 6.4708. Min Range: -6.4708

Max Act: 5.0625. Min Act: -0.0000

Data Index: 595403 (C4 (Web Text))

Max Activating Token Index: 457