Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2679 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.4085. Min Act: -0.0003

Data Index: 150381 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3785. Min Act: -0.0003

Data Index: 426097 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3508. Min Act: -0.0003

Data Index: 1219121 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3709. Min Act: -0.0003

Data Index: 1319654 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3491. Min Act: -0.0003

Data Index: 1231207 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3296. Min Act: -0.0003

Data Index: 242819 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3284. Min Act: -0.0003

Data Index: 177195 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3274. Min Act: -0.0003

Data Index: 98667 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3212. Min Act: -0.0003

Data Index: 233066 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3328. Min Act: -0.0002

Data Index: 1398162 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3205. Min Act: -0.0003

Data Index: 1275865 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3183. Min Act: -0.0003

Data Index: 1324090 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3105. Min Act: -0.0003

Data Index: 485654 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3081. Min Act: -0.0003

Data Index: 1027989 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3052. Min Act: -0.0003

Data Index: 839610 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3151. Min Act: -0.0003

Data Index: 78991 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3013. Min Act: -0.0003

Data Index: 1307451 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.3071. Min Act: -0.0002

Data Index: 876650 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.2973. Min Act: -0.0003

Data Index: 118190 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.4085. Min Range: -0.4085

Max Act: 0.2963. Min Act: -0.0003

Data Index: 189471 (C4 (Web Text))

Max Activating Token Index: 181