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

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

Neuron 4954 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.7234. Min Act: -0.0000

Data Index: 1362026 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.8968. Min Act: -0.0000

Data Index: 496707 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.7815. Min Act: -0.0000

Data Index: 148298 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.5105. Min Act: -0.0000

Data Index: 558065 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.5834. Min Act: -0.0000

Data Index: 306041 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.4622. Min Act: -0.0000

Data Index: 456676 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.3300. Min Act: -0.0000

Data Index: 542115 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.3525. Min Act: -0.0000

Data Index: 1133375 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.1579. Min Act: -0.0000

Data Index: 1216343 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.2828. Min Act: -0.0000

Data Index: 272210 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.2608. Min Act: -0.0000

Data Index: 1217763 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.2626. Min Act: -0.0000

Data Index: 1068222 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.1235. Min Act: -0.0000

Data Index: 834677 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.0100. Min Act: -0.0000

Data Index: 900532 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.1050. Min Act: -0.0000

Data Index: 775739 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.0971. Min Act: -0.0000

Data Index: 167537 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 2.8968. Min Range: -2.8968

Max Act: 1.9394. Min Act: -0.0000

Data Index: 1117353 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.0130. Min Act: -0.0000

Data Index: 1134027 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.1231. Min Act: -0.0000

Data Index: 949860 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 2.8968. Min Range: -2.8968

Max Act: 2.1106. Min Act: -0.0000

Data Index: 746098 (C4 (Web Text))

Max Activating Token Index: 524