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

Dataset: The Pile

Neuron 2408 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: 1.3969. Min Range: -1.3969

Max Act: 1.3969. Min Act: -0.0000

Data Index: 703755 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.3319. Min Act: -0.0000

Data Index: 1110583 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.3423. Min Act: -0.0000

Data Index: 337773 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.3841. Min Act: -0.0000

Data Index: 313115 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1827615 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1477480 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.3048. Min Act: -0.0000

Data Index: 259075 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.2137. Min Act: -0.0000

Data Index: 497515 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.1611. Min Act: -0.0000

Data Index: 138910 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0409. Min Act: -0.0000

Data Index: 547886 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.1193. Min Act: -0.0000

Data Index: 945692 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0632. Min Act: -0.0000

Data Index: 693656 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1610579 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 1.3969. Min Range: -1.3969

Max Act: 0.9738. Min Act: -0.0000

Data Index: 286011 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0152. Min Act: -0.0000

Data Index: 938222 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0808. Min Act: -0.0000

Data Index: 394338 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1608617 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.1278. Min Act: -0.0000

Data Index: 29854 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0593. Min Act: -0.0000

Data Index: 154979 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1972754 (The Pile)

Max Activating Token Index: 148