Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 159 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0006

Data Index: 75111 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0317. Min Act: -0.0006

Data Index: 727953 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0324. Min Act: -0.0006

Data Index: 546907 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0322. Min Act: -0.0006

Data Index: 858198 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0302. Min Act: -0.0006

Data Index: 659453 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0305. Min Act: -0.0006

Data Index: 21822 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0295. Min Act: -0.0006

Data Index: 979986 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0296. Min Act: -0.0006

Data Index: 854981 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1194383 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0289. Min Act: -0.0007

Data Index: 558056 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1259569 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1069127 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1040647 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0278. Min Act: -0.0006

Data Index: 369909 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0276. Min Act: -0.0006

Data Index: 491407 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0264. Min Act: -0.0006

Data Index: 343142 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0283. Min Act: -0.0006

Data Index: 492630 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0270. Min Act: -0.0006

Data Index: 409606 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1078685 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1028518 (C4 (Web Text))

Max Activating Token Index: 615