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

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

Neuron 2326 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4272. Min Act: -0.0001

Data Index: 636560 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3813. Min Act: -0.0001

Data Index: 39566 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4706. Min Act: -0.0001

Data Index: 177748 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4051. Min Act: -0.0001

Data Index: 398768 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3912. Min Act: -0.0001

Data Index: 1283350 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3862. Min Act: -0.0001

Data Index: 35316 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3644. Min Act: -0.0001

Data Index: 525916 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3391. Min Act: -0.0001

Data Index: 932160 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1357920 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1164112 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1110521 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3894. Min Act: -0.0001

Data Index: 484806 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3506. Min Act: -0.0001

Data Index: 330777 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3736. Min Act: -0.0001

Data Index: 549630 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3484. Min Act: -0.0001

Data Index: 706146 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3572. Min Act: -0.0001

Data Index: 714775 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3669. Min Act: -0.0001

Data Index: 526020 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3421. Min Act: -0.0001

Data Index: 847214 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3674. Min Act: -0.0001

Data Index: 883926 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3552. Min Act: -0.0001

Data Index: 253970 (C4 (Web Text))

Max Activating Token Index: 269