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

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

Neuron 5252 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: 1.8951. Min Range: -1.8951

Max Act: 1.8951. Min Act: -0.0000

Data Index: 1510041 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5857. Min Act: -0.0000

Data Index: 1398395 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1218342 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5024. Min Act: -0.0000

Data Index: 977740 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1274913 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5420. Min Act: -0.0000

Data Index: 790191 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.4376. Min Act: -0.0000

Data Index: 116740 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1647938 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3312. Min Act: -0.0000

Data Index: 304429 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1565505 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1651987 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2925. Min Act: -0.0000

Data Index: 16270 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3599. Min Act: -0.0000

Data Index: 60909 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3205. Min Act: -0.0000

Data Index: 469973 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2800. Min Act: -0.0000

Data Index: 218895 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1032195 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3315. Min Act: -0.0000

Data Index: 780799 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2951. Min Act: -0.0000

Data Index: 506567 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1141678 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2914. Min Act: -0.0000

Data Index: 892148 (C4 (Web Text))

Max Activating Token Index: 836