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

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

Neuron 4085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3679. Min Act: -0.0000

Data Index: 692117 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4059. Min Act: -0.0001

Data Index: 991950 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4332. Min Act: -0.0001

Data Index: 118520 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3761. Min Act: -0.0001

Data Index: 121998 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3347. Min Act: -0.0001

Data Index: 482545 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3695. Min Act: -0.0001

Data Index: 36394 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3423. Min Act: -0.0001

Data Index: 988724 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2266. Min Act: -0.0001

Data Index: 581616 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3205. Min Act: -0.0001

Data Index: 1291444 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2155. Min Act: -0.0001

Data Index: 637875 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2832. Min Act: -0.0001

Data Index: 1173342 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2932. Min Act: -0.0001

Data Index: 172480 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2169. Min Act: -0.0001

Data Index: 343366 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1755. Min Act: -0.0000

Data Index: 559410 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2029. Min Act: -0.0001

Data Index: 271720 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2289. Min Act: -0.0001

Data Index: 542989 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2540. Min Act: -0.0001

Data Index: 247797 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2066. Min Act: -0.0001

Data Index: 614632 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2364. Min Act: -0.0000

Data Index: 47331 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1635. Min Act: -0.0000

Data Index: 657500 (C4 (Web Text))

Max Activating Token Index: 825