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

Dataset: The Pile

Neuron 1499 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: 0.4000. Min Range: -0.4000

Max Act: 0.4000. Min Act: 0.0000

Data Index: 49182 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1137172 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3398. Min Act: 0.0000

Data Index: 1994513 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1114848 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3248. Min Act: 0.0000

Data Index: 322544 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3262. Min Act: 0.0000

Data Index: 72323 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3255. Min Act: 0.0000

Data Index: 176256 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3111. Min Act: -0.0000

Data Index: 968398 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3239. Min Act: 0.0000

Data Index: 1425604 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3079. Min Act: 0.0000

Data Index: 171654 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3157. Min Act: 0.0000

Data Index: 606733 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3084. Min Act: -0.0000

Data Index: 846962 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2990. Min Act: 0.0000

Data Index: 1201028 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3045. Min Act: 0.0001

Data Index: 153858 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3080. Min Act: 0.0000

Data Index: 708286 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1602821 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1544244 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3092. Min Act: 0.0000

Data Index: 1829461 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2962. Min Act: 0.0000

Data Index: 1356981 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3099. Min Act: 0.0000

Data Index: 831162 (The Pile)

Max Activating Token Index: 268