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

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

Neuron 2122 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: 0.4394. Min Range: -0.4394

Max Act: 0.4394. Min Act: -0.0001

Data Index: 538386 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3953. Min Act: -0.0001

Data Index: 72071 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3953. Min Act: -0.0001

Data Index: 659899 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1367337 (Python Code)

Max Activating Token Index: 375

Text #4

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3704. Min Act: -0.0001

Data Index: 1452229 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3402. Min Act: -0.0001

Data Index: 100114 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3379. Min Act: -0.0001

Data Index: 1448859 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1414777 (Python Code)

Max Activating Token Index: 745

Text #8

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1119140 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3489. Min Act: -0.0001

Data Index: 1516507 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3127. Min Act: -0.0001

Data Index: 1505005 (Python Code)

Max Activating Token Index: 1015

Text #11

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1584967 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3202. Min Act: -0.0001

Data Index: 1541315 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3070. Min Act: -0.0001

Data Index: 1455050 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3086. Min Act: -0.0001

Data Index: 1400339 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1035702 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1628549 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1427634 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1643661 (Python Code)

Max Activating Token Index: 980

Text #19

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1606195 (Python Code)

Max Activating Token Index: 283