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

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

Neuron 283 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.8934. Min Act: -0.0000

Data Index: 340186 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.5958. Min Act: -0.0000

Data Index: 194449 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.5293. Min Act: -0.0000

Data Index: 383504 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.0057. Min Act: -0.0000

Data Index: 1068924 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.8554. Min Act: -0.0000

Data Index: 983008 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.6244. Min Act: -0.0000

Data Index: 409062 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.6037. Min Act: -0.0000

Data Index: 167168 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.7348. Min Act: -0.0000

Data Index: 373978 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.6952. Min Act: -0.0000

Data Index: 298434 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.6204. Min Act: -0.0000

Data Index: 280828 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.5925. Min Act: -0.0000

Data Index: 1347039 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.5862. Min Act: -0.0000

Data Index: 1087675 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.4205. Min Act: -0.0000

Data Index: 679897 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.6627. Min Act: -0.0000

Data Index: 694642 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.5402. Min Act: -0.0000

Data Index: 62467 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.5063. Min Act: -0.0000

Data Index: 372447 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.3343. Min Act: -0.0000

Data Index: 902698 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.4655. Min Act: -0.0000

Data Index: 1182219 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.4405. Min Act: -0.0000

Data Index: 729106 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 3.8934. Min Range: -3.8934

Max Act: 2.3451. Min Act: -0.0000

Data Index: 574079 (C4 (Web Text))

Max Activating Token Index: 878