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

Dataset: The Pile

Neuron 1396 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.4059. Min Act: -0.0000

Data Index: 743896 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3948. Min Act: -0.0000

Data Index: 929687 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1493179 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1165369 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1530211 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1455216 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3422. Min Act: -0.0000

Data Index: 194691 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1350930 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3292. Min Act: 0.0000

Data Index: 945821 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3610. Min Act: -0.0000

Data Index: 954934 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1478520 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3321. Min Act: -0.0000

Data Index: 193380 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3296. Min Act: 0.0001

Data Index: 1705173 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1535759 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3379. Min Act: 0.0000

Data Index: 896945 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3204. Min Act: -0.0000

Data Index: 833949 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3201. Min Act: -0.0000

Data Index: 437356 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1955677 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3054. Min Act: -0.0000

Data Index: 252122 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3136. Min Act: -0.0000

Data Index: 127108 (The Pile)

Max Activating Token Index: 117