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

Dataset: The Pile

Neuron 2100 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: 0.4066. Min Range: -0.4066

Max Act: 0.4066. Min Act: -0.0000

Data Index: 751284 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3532. Min Act: -0.0000

Data Index: 923554 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3036. Min Act: -0.0000

Data Index: 505358 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1046413 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2528. Min Act: -0.0000

Data Index: 910287 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2817. Min Act: -0.0000

Data Index: 895956 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1339201 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2596. Min Act: -0.0000

Data Index: 37730 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2470. Min Act: -0.0000

Data Index: 150734 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1379315 (The Pile)

Max Activating Token Index: 195

Text #10

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1627155 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2306. Min Act: -0.0000

Data Index: 140790 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2341. Min Act: -0.0000

Data Index: 21331 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2368. Min Act: -0.0000

Data Index: 61011 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1195407 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2129. Min Act: -0.0000

Data Index: 304291 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1202803 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2214. Min Act: -0.0000

Data Index: 438947 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1363148 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1423177 (The Pile)

Max Activating Token Index: 45