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

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

Neuron 3634 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1350339 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3576. Min Act: -0.0000

Data Index: 281361 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1073039 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.4000. Min Act: -0.0000

Data Index: 555748 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1039092 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3949. Min Act: -0.0000

Data Index: 1289114 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3107. Min Act: -0.0000

Data Index: 739235 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3868. Min Act: -0.0000

Data Index: 1332045 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3763. Min Act: -0.0000

Data Index: 964946 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3260. Min Act: -0.0000

Data Index: 1074952 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.2552. Min Act: -0.0000

Data Index: 10587 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3205. Min Act: -0.0000

Data Index: 109450 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.2698. Min Act: -0.0000

Data Index: 890970 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.2596. Min Act: -0.0000

Data Index: 365494 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3310. Min Act: -0.0000

Data Index: 953050 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3814. Min Act: -0.0000

Data Index: 726402 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3413. Min Act: -0.0000

Data Index: 235582 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.2831. Min Act: -0.0000

Data Index: 143176 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.2748. Min Act: -0.0000

Data Index: 1154414 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1080511 (C4 (Web Text))

Max Activating Token Index: 58