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

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

Neuron 2304 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0000

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0874. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0703. Min Act: -0.0001

Data Index: 178691 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0740. Min Act: -0.0000

Data Index: 944441 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1139988 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1418656 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0680. Min Act: -0.0001

Data Index: 169367 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0580. Min Act: -0.0000

Data Index: 831894 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0693. Min Act: -0.0000

Data Index: 539993 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1218511 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0639. Min Act: -0.0000

Data Index: 69307 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0697. Min Act: -0.0000

Data Index: 38833 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1103654 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0591. Min Act: -0.0000

Data Index: 659333 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1283354 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1100004 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0542. Min Act: -0.0000

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1643948 (Python Code)

Max Activating Token Index: 491