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

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

Neuron 5541 in Layer 1

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: 1.6236. Min Range: -1.6236

Max Act: 1.6236. Min Act: -0.0002

Data Index: 384232 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.6077. Min Act: -0.0003

Data Index: 222097 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.5662. Min Act: -0.0003

Data Index: 1170695 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.5443. Min Act: -0.0002

Data Index: 1256641 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.5946. Min Act: -0.0002

Data Index: 1226624 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.5267. Min Act: -0.0002

Data Index: 48533 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.5267. Min Act: -0.0002

Data Index: 1227436 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4887. Min Act: -0.0003

Data Index: 957225 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4757. Min Act: -0.0002

Data Index: 1272551 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4731. Min Act: -0.0002

Data Index: 662206 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4505. Min Act: -0.0002

Data Index: 471106 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4247. Min Act: -0.0002

Data Index: 868056 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4138. Min Act: -0.0002

Data Index: 187151 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4308. Min Act: -0.0003

Data Index: 276714 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.4242. Min Act: -0.0002

Data Index: 638870 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3793. Min Act: -0.0002

Data Index: 173968 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3940. Min Act: -0.0003

Data Index: 531100 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3734. Min Act: -0.0002

Data Index: 1053343 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3861. Min Act: -0.0002

Data Index: 837315 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3757. Min Act: -0.0002

Data Index: 90993 (C4 (Web Text))

Max Activating Token Index: 135