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

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

Neuron 171 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6119. Min Range: -2.6119

Max Act: 2.6119. Min Act: -0.0000

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 2.6119. Min Range: -2.6119

Max Act: 2.2161. Min Act: -0.0000

Data Index: 1018048 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 2.6119. Min Range: -2.6119

Max Act: 2.1723. Min Act: -0.0000

Data Index: 205451 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.9909. Min Act: -0.0000

Data Index: 593234 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.9478. Min Act: -0.0000

Data Index: 461371 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.9327. Min Act: -0.0000

Data Index: 700443 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.9045. Min Act: -0.0000

Data Index: 1173023 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.8978. Min Act: -0.0000

Data Index: 671096 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.7365. Min Act: -0.0000

Data Index: 850905 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1061596 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.7356. Min Act: -0.0000

Data Index: 180549 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.7240. Min Act: -0.0000

Data Index: 562583 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.6261. Min Act: -0.0000

Data Index: 708102 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.5907. Min Act: -0.0000

Data Index: 1080648 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.6840. Min Act: -0.0000

Data Index: 865301 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1189063 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.5277. Min Act: -0.0000

Data Index: 619557 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.6187. Min Act: -0.0000

Data Index: 53533 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.6191. Min Act: -0.0000

Data Index: 813387 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 2.6119. Min Range: -2.6119

Max Act: 1.5206. Min Act: -0.0000

Data Index: 219254 (C4 (Web Text))

Max Activating Token Index: 260