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

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

Neuron 3387 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: 0.9036. Min Range: -0.9036

Max Act: 0.9036. Min Act: -0.0001

Data Index: 535616 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8953. Min Act: -0.0001

Data Index: 1328248 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8491. Min Act: -0.0001

Data Index: 917985 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8487. Min Act: -0.0001

Data Index: 638666 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8301. Min Act: -0.0001

Data Index: 1321314 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8064. Min Act: -0.0001

Data Index: 95427 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8032. Min Act: -0.0001

Data Index: 1241443 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7731. Min Act: -0.0001

Data Index: 212103 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7555. Min Act: -0.0001

Data Index: 662825 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7582. Min Act: -0.0001

Data Index: 335171 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7489. Min Act: -0.0001

Data Index: 864969 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7548. Min Act: -0.0001

Data Index: 773874 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7433. Min Act: -0.0001

Data Index: 260453 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1068769 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7401. Min Act: -0.0001

Data Index: 343954 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7391. Min Act: -0.0001

Data Index: 382398 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7375. Min Act: -0.0001

Data Index: 815880 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7312. Min Act: -0.0001

Data Index: 852065 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7181. Min Act: -0.0001

Data Index: 767587 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7120. Min Act: -0.0001

Data Index: 1019210 (C4 (Web Text))

Max Activating Token Index: 276