Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 928 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1303296 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2710. Min Act: -0.0000

Data Index: 507603 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1929739 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2417. Min Act: -0.0000

Data Index: 450247 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2368. Min Act: -0.0000

Data Index: 587353 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2275. Min Act: -0.0000

Data Index: 315921 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1555782 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2036. Min Act: -0.0000

Data Index: 588626 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1128515 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2240. Min Act: -0.0000

Data Index: 577991 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2167. Min Act: -0.0000

Data Index: 805115 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2001. Min Act: -0.0000

Data Index: 741355 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2097. Min Act: -0.0000

Data Index: 79839 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2160. Min Act: -0.0000

Data Index: 242260 (The Pile)

Max Activating Token Index: 427

Text #14

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2202. Min Act: -0.0000

Data Index: 372930 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2117. Min Act: -0.0000

Data Index: 67342 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1939149 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.1804. Min Act: -0.0000

Data Index: 274741 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1556190 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.1894. Min Act: 0.0000

Data Index: 182258 (The Pile)

Max Activating Token Index: 309