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

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

Neuron 3338 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: 0.2849. Min Range: -0.2849

Max Act: 0.2849. Min Act: -0.0001

Data Index: 190605 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2774. Min Act: -0.0001

Data Index: 375162 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1299470 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2559. Min Act: -0.0001

Data Index: 162476 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2512. Min Act: -0.0001

Data Index: 1017203 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1323011 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2457. Min Act: -0.0001

Data Index: 891310 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1109157 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1302190 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2431. Min Act: -0.0001

Data Index: 252434 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2442. Min Act: -0.0001

Data Index: 12919 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2401. Min Act: -0.0001

Data Index: 470591 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2445. Min Act: -0.0001

Data Index: 35332 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2418. Min Act: -0.0001

Data Index: 986902 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2330. Min Act: -0.0001

Data Index: 234196 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2356. Min Act: -0.0001

Data Index: 1209618 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2400. Min Act: -0.0001

Data Index: 360892 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2330. Min Act: -0.0001

Data Index: 1548115 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1018469 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2348. Min Act: -0.0001

Data Index: 1361597 (Python Code)

Max Activating Token Index: 886