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

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

Neuron 3149 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5682. Min Act: -0.0000

Data Index: 587395 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5081. Min Act: -0.0000

Data Index: 183309 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4884. Min Act: -0.0001

Data Index: 394165 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1023682 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4725. Min Act: -0.0000

Data Index: 900181 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4461. Min Act: -0.0000

Data Index: 315021 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1118758 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4228. Min Act: -0.0000

Data Index: 260670 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4326. Min Act: -0.0000

Data Index: 40920 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4012. Min Act: -0.0000

Data Index: 899312 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3772. Min Act: -0.0000

Data Index: 589130 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3374. Min Act: -0.0000

Data Index: 944398 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3395. Min Act: -0.0000

Data Index: 363604 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1236486 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3386. Min Act: -0.0000

Data Index: 740273 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3489. Min Act: -0.0000

Data Index: 394550 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3503. Min Act: -0.0000

Data Index: 225743 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3266. Min Act: -0.0000

Data Index: 574705 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3111. Min Act: -0.0000

Data Index: 29104 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1204396 (C4 (Web Text))

Max Activating Token Index: 296