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

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

Neuron 649 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.4063. Min Act: -0.0001

Data Index: 1037621 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2949. Min Act: -0.0001

Data Index: 432291 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2701. Min Act: -0.0001

Data Index: 109662 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1188082 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2487. Min Act: -0.0001

Data Index: 178298 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1180855 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2360. Min Act: -0.0001

Data Index: 695871 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2329. Min Act: -0.0001

Data Index: 986770 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1317774 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2386. Min Act: -0.0001

Data Index: 836555 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2330. Min Act: -0.0001

Data Index: 1089676 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2253. Min Act: -0.0001

Data Index: 130241 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1204221 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2223. Min Act: -0.0001

Data Index: 245330 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1295200 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2065. Min Act: -0.0001

Data Index: 249028 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2066. Min Act: -0.0001

Data Index: 501258 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1200971 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2066. Min Act: -0.0001

Data Index: 7626 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2024. Min Act: -0.0001

Data Index: 1060493 (C4 (Web Text))

Max Activating Token Index: 183