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

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

Neuron 782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1232108 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.4761. Min Act: -0.0001

Data Index: 976117 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.4255. Min Act: -0.0001

Data Index: 75718 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3931. Min Act: -0.0000

Data Index: 300776 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3594. Min Act: -0.0001

Data Index: 131417 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3197. Min Act: -0.0000

Data Index: 549706 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3119. Min Act: -0.0001

Data Index: 654578 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1259402 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3152. Min Act: -0.0001

Data Index: 199811 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3498. Min Act: -0.0001

Data Index: 1209622 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3289. Min Act: -0.0001

Data Index: 424276 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3269. Min Act: -0.0001

Data Index: 288513 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3427. Min Act: -0.0000

Data Index: 690603 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3050. Min Act: -0.0001

Data Index: 846614 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3095. Min Act: -0.0001

Data Index: 873722 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1065045 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3035. Min Act: -0.0001

Data Index: 761946 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3017. Min Act: -0.0000

Data Index: 664996 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3253. Min Act: -0.0001

Data Index: 716450 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.2792. Min Act: -0.0001

Data Index: 859959 (C4 (Web Text))

Max Activating Token Index: 304