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

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

Neuron 1866 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.8479. Min Act: -0.0001

Data Index: 1234222 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6439. Min Act: -0.0001

Data Index: 1269719 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.8030. Min Act: -0.0001

Data Index: 592458 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7008. Min Act: -0.0001

Data Index: 1168545 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6459. Min Act: -0.0001

Data Index: 1185991 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6863. Min Act: -0.0001

Data Index: 439536 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6182. Min Act: -0.0001

Data Index: 655353 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6070. Min Act: -0.0001

Data Index: 196207 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4404. Min Act: -0.0001

Data Index: 1293699 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4367. Min Act: -0.0001

Data Index: 1009852 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4321. Min Act: -0.0001

Data Index: 677116 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5283. Min Act: -0.0001

Data Index: 626859 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5012. Min Act: -0.0001

Data Index: 91449 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5443. Min Act: -0.0001

Data Index: 795311 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.3790. Min Act: -0.0001

Data Index: 570502 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.2801. Min Act: -0.0001

Data Index: 1005545 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.3993. Min Act: -0.0001

Data Index: 662806 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4387. Min Act: -0.0001

Data Index: 1306111 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4452. Min Act: -0.0001

Data Index: 723622 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5740. Min Act: -0.0001

Data Index: 545132 (C4 (Web Text))

Max Activating Token Index: 240