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

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

Neuron 437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3710. Min Act: -0.0001

Data Index: 879677 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.4113. Min Act: -0.0001

Data Index: 508888 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3630. Min Act: -0.0001

Data Index: 953002 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3884. Min Act: -0.0001

Data Index: 540551 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3843. Min Act: -0.0001

Data Index: 558274 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3721. Min Act: -0.0001

Data Index: 504031 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3716. Min Act: -0.0001

Data Index: 1289234 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3677. Min Act: -0.0001

Data Index: 610320 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3754. Min Act: -0.0001

Data Index: 120938 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3626. Min Act: -0.0001

Data Index: 267809 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3596. Min Act: -0.0001

Data Index: 360487 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3835. Min Act: -0.0001

Data Index: 347709 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3729. Min Act: -0.0001

Data Index: 242778 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3588. Min Act: -0.0001

Data Index: 677532 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3613. Min Act: -0.0001

Data Index: 114950 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3589. Min Act: -0.0001

Data Index: 297405 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1308469 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3549. Min Act: -0.0001

Data Index: 359760 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3531. Min Act: -0.0001

Data Index: 1352315 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.4113. Min Range: -0.4113

Max Act: 0.3183. Min Act: -0.0001

Data Index: 552292 (C4 (Web Text))

Max Activating Token Index: 684