Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2942 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4155. Min Range: -1.4155

Max Act: 1.4155. Min Act: -0.0000

Data Index: 1407469 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 1.4155. Min Range: -1.4155

Max Act: 1.3240. Min Act: -0.0000

Data Index: 719597 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 1.4155. Min Range: -1.4155

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1407984 (Python Code)

Max Activating Token Index: 254

Text #3

Max Range: 1.4155. Min Range: -1.4155

Max Act: 1.0977. Min Act: -0.0000

Data Index: 838341 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.4155. Min Range: -1.4155

Max Act: 1.1699. Min Act: -0.0000

Data Index: 175473 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.4155. Min Range: -1.4155

Max Act: 1.1728. Min Act: -0.0000

Data Index: 746747 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1173947 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9519. Min Act: -0.0000

Data Index: 863195 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9846. Min Act: -0.0000

Data Index: 310110 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9486. Min Act: -0.0000

Data Index: 422153 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9524. Min Act: -0.0000

Data Index: 234343 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9573. Min Act: -0.0000

Data Index: 338249 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9202. Min Act: -0.0000

Data Index: 280533 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9210. Min Act: -0.0000

Data Index: 709846 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1535986 (Python Code)

Max Activating Token Index: 966

Text #15

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.9864. Min Act: -0.0000

Data Index: 182217 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1412296 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.8583. Min Act: -0.0000

Data Index: 127870 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1474687 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 1.4155. Min Range: -1.4155

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1448767 (Python Code)

Max Activating Token Index: 271