Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4331 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1160753 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.7051. Min Act: 0.0000

Data Index: 456916 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.7293. Min Act: -0.0000

Data Index: 960259 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6520. Min Act: -0.0000

Data Index: 664061 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5951. Min Act: 0.0001

Data Index: 1104600 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1337309 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6006. Min Act: -0.0000

Data Index: 126685 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1202956 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5887. Min Act: 0.0000

Data Index: 394061 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5574. Min Act: -0.0000

Data Index: 839592 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5450. Min Act: -0.0000

Data Index: 94464 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5487. Min Act: -0.0000

Data Index: 378371 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5297. Min Act: -0.0000

Data Index: 81019 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5161. Min Act: -0.0000

Data Index: 113926 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5283. Min Act: 0.0001

Data Index: 1121800 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5181. Min Act: 0.0000

Data Index: 965231 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1261084 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5027. Min Act: -0.0000

Data Index: 358310 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.4940. Min Act: -0.0000

Data Index: 957222 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5150. Min Act: -0.0000

Data Index: 862633 (C4 (Web Text))

Max Activating Token Index: 615