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

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

Neuron 4924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4965. Min Act: -0.0000

Data Index: 895634 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4624. Min Act: -0.0000

Data Index: 563407 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4802. Min Act: -0.0000

Data Index: 489554 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4644. Min Act: -0.0000

Data Index: 890712 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4422. Min Act: -0.0000

Data Index: 866574 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4583. Min Act: -0.0000

Data Index: 406386 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4240. Min Act: -0.0000

Data Index: 972989 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4316. Min Act: -0.0000

Data Index: 491664 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1046664 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4150. Min Act: -0.0000

Data Index: 835958 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4402. Min Act: -0.0000

Data Index: 109907 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1349454 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4377. Min Act: -0.0000

Data Index: 932218 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4211. Min Act: -0.0000

Data Index: 210563 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4114. Min Act: -0.0000

Data Index: 531703 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4481. Min Act: -0.0000

Data Index: 574966 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4179. Min Act: -0.0000

Data Index: 524464 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4152. Min Act: -0.0000

Data Index: 746553 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1026517 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1093050 (C4 (Web Text))

Max Activating Token Index: 1005