Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1400 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.8191. Min Act: -0.0006

Data Index: 719166 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.8114. Min Act: -0.0006

Data Index: 436559 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7807. Min Act: -0.0006

Data Index: 359846 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7126. Min Act: -0.0006

Data Index: 36950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7156. Min Act: -0.0006

Data Index: 1291075 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7594. Min Act: -0.0006

Data Index: 392125 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7537. Min Act: -0.0006

Data Index: 1072429 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7404. Min Act: -0.0006

Data Index: 772357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7393. Min Act: -0.0006

Data Index: 640431 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7334. Min Act: -0.0006

Data Index: 495550 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.6822. Min Act: -0.0006

Data Index: 250681 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7226. Min Act: -0.0006

Data Index: 762190 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7279. Min Act: -0.0006

Data Index: 730345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7238. Min Act: -0.0006

Data Index: 930835 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7201. Min Act: -0.0006

Data Index: 714107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.6739. Min Act: -0.0006

Data Index: 278387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7115. Min Act: -0.0006

Data Index: 524026 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.6659. Min Act: -0.0006

Data Index: 971607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.6976. Min Act: -0.0006

Data Index: 422019 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.8191. Min Range: -1.8191

Max Act: 1.7406. Min Act: -0.0006

Data Index: 902553 (C4 (Web Text))

Max Activating Token Index: 1023