Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4665. Min Act: -0.0000

Data Index: 348937 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4561. Min Act: -0.0000

Data Index: 573768 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4532. Min Act: -0.0000

Data Index: 772193 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1122836 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1141214 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4197. Min Act: -0.0000

Data Index: 694599 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4330. Min Act: -0.0001

Data Index: 566818 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4284. Min Act: -0.0000

Data Index: 358515 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3979. Min Act: -0.0001

Data Index: 1157066 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4034. Min Act: -0.0000

Data Index: 73204 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3694. Min Act: -0.0000

Data Index: 656213 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4071. Min Act: -0.0000

Data Index: 137315 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3935. Min Act: -0.0000

Data Index: 831081 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3869. Min Act: -0.0000

Data Index: 705039 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3784. Min Act: -0.0000

Data Index: 770868 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1009071 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3935. Min Act: -0.0000

Data Index: 869746 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3934. Min Act: -0.0000

Data Index: 62132 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3916. Min Act: -0.0000

Data Index: 414946 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1240897 (C4 (Web Text))

Max Activating Token Index: 314