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

Dataset: The Pile

Neuron 304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.7672. Min Act: -0.0000

Data Index: 104684 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5740. Min Act: -0.0000

Data Index: 303830 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5155. Min Act: -0.0000

Data Index: 325124 (The Pile)

Max Activating Token Index: 402

Text #3

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5805. Min Act: -0.0000

Data Index: 732555 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.6389. Min Act: -0.0000

Data Index: 502553 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1584705 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.4517. Min Act: -0.0000

Data Index: 284836 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5191. Min Act: -0.0000

Data Index: 78004 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.4312. Min Act: -0.0000

Data Index: 1713400 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1545189 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5401. Min Act: -0.0000

Data Index: 1312134 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5481. Min Act: -0.0000

Data Index: 886757 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.6441. Min Act: -0.0000

Data Index: 564018 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.4503. Min Act: -0.0000

Data Index: 509328 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1260804 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5428. Min Act: -0.0000

Data Index: 1155045 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.5331. Min Act: -0.0000

Data Index: 374537 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1019231 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.3373. Min Act: -0.0000

Data Index: 1419943 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 1.7672. Min Range: -1.7672

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1939090 (The Pile)

Max Activating Token Index: 532