Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0003

Data Index: 543493 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0950. Min Act: -0.0003

Data Index: 134403 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0003

Data Index: 211380 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0916. Min Act: -0.0003

Data Index: 393147 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0932. Min Act: -0.0004

Data Index: 535064 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0915. Min Act: -0.0003

Data Index: 351610 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0878. Min Act: -0.0003

Data Index: 645086 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0778. Min Act: -0.0003

Data Index: 1005018 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0808. Min Act: -0.0003

Data Index: 26746 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0810. Min Act: -0.0003

Data Index: 234042 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1028037 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0759. Min Act: -0.0003

Data Index: 142077 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0808. Min Act: -0.0003

Data Index: 775937 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0778. Min Act: -0.0003

Data Index: 1071236 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1190232 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1327243 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1310926 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0751. Min Act: -0.0003

Data Index: 110591 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0765. Min Act: -0.0004

Data Index: 859327 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0741. Min Act: -0.0004

Data Index: 170457 (C4 (Web Text))

Max Activating Token Index: 596