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

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

Neuron 2775 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5916. Min Range: -3.5916

Max Act: 3.5916. Min Act: -0.0000

Data Index: 28988 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.6318. Min Act: -0.0000

Data Index: 187312 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.4897. Min Act: -0.0000

Data Index: 1468926 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.4298. Min Act: -0.0000

Data Index: 1240166 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.3925. Min Act: -0.0000

Data Index: 456015 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.3044. Min Act: -0.0000

Data Index: 1525278 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.2704. Min Act: -0.0000

Data Index: 816777 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.2291. Min Act: -0.0000

Data Index: 1008105 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.2223. Min Act: -0.0000

Data Index: 436222 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.2147. Min Act: -0.0000

Data Index: 666199 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.3459. Min Act: -0.0000

Data Index: 430329 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.1785. Min Act: -0.0000

Data Index: 583613 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.1652. Min Act: -0.0000

Data Index: 844209 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.1421. Min Act: -0.0000

Data Index: 224971 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.1121. Min Act: -0.0000

Data Index: 314613 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 3.5916. Min Range: -3.5916

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1334198 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.0449. Min Act: -0.0000

Data Index: 1352438 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 3.5916. Min Range: -3.5916

Max Act: 2.1074. Min Act: -0.0000

Data Index: 831282 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 3.5916. Min Range: -3.5916

Max Act: 1.9610. Min Act: -0.0000

Data Index: 38298 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 3.5916. Min Range: -3.5916

Max Act: 1.9692. Min Act: -0.0000

Data Index: 1399941 (Python Code)

Max Activating Token Index: 281