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

Dataset: The Pile

Neuron 3025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4361. Min Range: -5.4361

Max Act: 5.4361. Min Act: -0.0000

Data Index: 1518290 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 5.4361. Min Range: -5.4361

Max Act: 5.1097. Min Act: -0.0000

Data Index: 349988 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 5.4361. Min Range: -5.4361

Max Act: 5.1825. Min Act: -0.0000

Data Index: 474374 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.9846. Min Act: -0.0000

Data Index: 254246 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.7644. Min Act: -0.0000

Data Index: 77555 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.7193. Min Act: -0.0000

Data Index: 703069 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 5.4361. Min Range: -5.4361

Max Act: 5.0845. Min Act: -0.0000

Data Index: 1835725 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.4585. Min Act: -0.0000

Data Index: 1018126 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.4631. Min Act: -0.0000

Data Index: 328080 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.2461. Min Act: -0.0000

Data Index: 1220756 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.4816. Min Act: -0.0000

Data Index: 977939 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.7045. Min Act: -0.0000

Data Index: 666487 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.6421. Min Act: -0.0000

Data Index: 976196 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.0946. Min Act: -0.0000

Data Index: 1877486 (The Pile)

Max Activating Token Index: 107

Text #14

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.5983. Min Act: -0.0000

Data Index: 1458937 (The Pile)

Max Activating Token Index: 414

Text #15

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.6451. Min Act: -0.0000

Data Index: 583331 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.5040. Min Act: -0.0000

Data Index: 731556 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.5481. Min Act: -0.0000

Data Index: 483319 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.3595. Min Act: -0.0000

Data Index: 1090847 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.5655. Min Act: -0.0000

Data Index: 1551767 (The Pile)

Max Activating Token Index: 414