Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2290 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0001

Data Index: 321359 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0540. Min Act: -0.0001

Data Index: 253803 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0508. Min Act: -0.0001

Data Index: 238232 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0501. Min Act: -0.0001

Data Index: 264157 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1214618 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0464. Min Act: -0.0001

Data Index: 986110 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0493. Min Act: -0.0001

Data Index: 73744 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0489. Min Act: -0.0001

Data Index: 86667 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0487. Min Act: -0.0001

Data Index: 261987 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0484. Min Act: -0.0001

Data Index: 105247 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1138198 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1226252 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0476. Min Act: -0.0001

Data Index: 986210 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1161847 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0507. Min Act: -0.0001

Data Index: 185988 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0469. Min Act: -0.0001

Data Index: 36203 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0449. Min Act: -0.0001

Data Index: 463582 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1397900 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0460. Min Act: -0.0001

Data Index: 943551 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0510. Min Act: -0.0001

Data Index: 120131 (C4 (Web Text))

Max Activating Token Index: 261