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

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

Neuron 3478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4943. Min Act: -0.0000

Data Index: 927873 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3588. Min Act: -0.0001

Data Index: 663194 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3542. Min Act: -0.0001

Data Index: 1082735 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3430. Min Act: -0.0000

Data Index: 737931 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3310. Min Act: -0.0001

Data Index: 291149 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3181. Min Act: -0.0001

Data Index: 268252 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1030349 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3373. Min Act: -0.0001

Data Index: 330191 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3152. Min Act: -0.0000

Data Index: 74174 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1313132 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3101. Min Act: -0.0001

Data Index: 215788 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1353579 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.2914. Min Act: -0.0000

Data Index: 770631 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1262593 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3000. Min Act: -0.0000

Data Index: 993515 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1161215 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.3090. Min Act: -0.0001

Data Index: 421948 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.2847. Min Act: -0.0001

Data Index: 989968 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.2984. Min Act: -0.0001

Data Index: 812484 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.2810. Min Act: -0.0001

Data Index: 232234 (C4 (Web Text))

Max Activating Token Index: 918