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

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

Neuron 3793 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1140761 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1376344 (Python Code)

Max Activating Token Index: 240

Text #2

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6065. Min Act: -0.0000

Data Index: 412537 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5417. Min Act: -0.0000

Data Index: 347493 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1205234 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1181206 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4921. Min Act: -0.0000

Data Index: 526183 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4480. Min Act: -0.0000

Data Index: 506642 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1354433 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4350. Min Act: -0.0000

Data Index: 24980 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1391150 (Python Code)

Max Activating Token Index: 435

Text #11

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1146379 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1212188 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1644086 (Python Code)

Max Activating Token Index: 595

Text #14

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4009. Min Act: -0.0000

Data Index: 854025 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1249103 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.3525. Min Act: -0.0000

Data Index: 517361 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1327243 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1647714 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.3854. Min Act: -0.0000

Data Index: 331606 (C4 (Web Text))

Max Activating Token Index: 780