Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1924 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2299. Min Range: -2.2299

Max Act: 2.2299. Min Act: -0.0000

Data Index: 789107 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9352. Min Act: -0.0000

Data Index: 1166169 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.6427. Min Act: -0.0001

Data Index: 112902 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.5474. Min Act: -0.0001

Data Index: 439589 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.7816. Min Act: -0.0000

Data Index: 565294 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.5420. Min Act: -0.0000

Data Index: 445489 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1096700 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.4002. Min Act: -0.0000

Data Index: 388934 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.4766. Min Act: -0.0001

Data Index: 67826 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.3862. Min Act: -0.0000

Data Index: 908885 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.3401. Min Act: -0.0000

Data Index: 649655 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.3172. Min Act: -0.0000

Data Index: 28590 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.4411. Min Act: -0.0000

Data Index: 531002 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.4459. Min Act: -0.0000

Data Index: 708262 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.3418. Min Act: -0.0000

Data Index: 36058 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.2474. Min Act: -0.0000

Data Index: 566022 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.3288. Min Act: -0.0000

Data Index: 526182 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.2547. Min Act: -0.0000

Data Index: 1047516 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.2825. Min Act: -0.0000

Data Index: 1187125 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.2073. Min Act: -0.0000

Data Index: 227279 (C4 (Web Text))

Max Activating Token Index: 75