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

Dataset: The Pile

Neuron 2447 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: 0.9961. Min Range: -0.9961

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1761418 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9961. Min Act: -0.0000

Data Index: 348874 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9026. Min Act: -0.0000

Data Index: 490823 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8075. Min Act: -0.0000

Data Index: 773177 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8650. Min Act: -0.0000

Data Index: 944216 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1352326 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8313. Min Act: -0.0000

Data Index: 567646 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8173. Min Act: -0.0000

Data Index: 724616 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1085021 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1840956 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1512731 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8446. Min Act: -0.0000

Data Index: 527171 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1744213 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7825. Min Act: -0.0000

Data Index: 651088 (The Pile)

Max Activating Token Index: 241

Text #14

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1714116 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7213. Min Act: -0.0000

Data Index: 343418 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7372. Min Act: -0.0000

Data Index: 442843 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1961615 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1993370 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7049. Min Act: -0.0000

Data Index: 706146 (The Pile)

Max Activating Token Index: 534