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

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

Neuron 3481 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2854. Min Act: -0.0001

Data Index: 477849 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2903. Min Act: -0.0000

Data Index: 484075 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2627. Min Act: -0.0001

Data Index: 1156305 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2490. Min Act: -0.0001

Data Index: 804175 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1243871 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2296. Min Act: -0.0001

Data Index: 20247 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1324752 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2486. Min Act: -0.0001

Data Index: 113630 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2620. Min Act: -0.0000

Data Index: 122135 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2280. Min Act: -0.0001

Data Index: 863284 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1118415 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1198525 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2545. Min Act: -0.0001

Data Index: 1152863 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2436. Min Act: -0.0001

Data Index: 1068543 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2330. Min Act: -0.0000

Data Index: 655555 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1295370 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2317. Min Act: -0.0001

Data Index: 155256 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2391. Min Act: -0.0000

Data Index: 191402 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2388. Min Act: -0.0001

Data Index: 797973 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2295. Min Act: -0.0001

Data Index: 299437 (C4 (Web Text))

Max Activating Token Index: 538