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

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

Neuron 1232 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5540. Min Act: -0.0000

Data Index: 376234 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5130. Min Act: -0.0000

Data Index: 649774 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1418681 (Python Code)

Max Activating Token Index: 423

Text #3

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4547. Min Act: -0.0000

Data Index: 417744 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1271491 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4272. Min Act: -0.0000

Data Index: 63618 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1133271 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4549. Min Act: -0.0000

Data Index: 785203 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4044. Min Act: -0.0000

Data Index: 426827 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1489544 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4346. Min Act: -0.0000

Data Index: 775393 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4135. Min Act: -0.0000

Data Index: 975030 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1467886 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4099. Min Act: -0.0000

Data Index: 110353 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3909. Min Act: -0.0000

Data Index: 15004 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3905. Min Act: -0.0000

Data Index: 373068 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1294765 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1445045 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1344025 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1288172 (C4 (Web Text))

Max Activating Token Index: 324