Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1186 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.7939. Min Act: -0.0000

Data Index: 786158 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.5143. Min Act: -0.0000

Data Index: 1467444 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.7488. Min Act: -0.0000

Data Index: 1958 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.5957. Min Act: -0.0000

Data Index: 1617046 (Python Code)

Max Activating Token Index: 338

Text #4

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.6119. Min Act: -0.0000

Data Index: 332439 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.5459. Min Act: -0.0000

Data Index: 140100 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.5137. Min Act: -0.0000

Data Index: 1246595 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.6227. Min Act: -0.0000

Data Index: 1429826 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.4776. Min Act: -0.0000

Data Index: 651064 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.4834. Min Act: -0.0000

Data Index: 234734 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.4638. Min Act: -0.0000

Data Index: 651253 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.4392. Min Act: -0.0000

Data Index: 1588613 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.1990. Min Act: -0.0000

Data Index: 777918 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.4173. Min Act: -0.0000

Data Index: 69071 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.2795. Min Act: -0.0000

Data Index: 1366077 (Python Code)

Max Activating Token Index: 994

Text #15

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.3761. Min Act: -0.0000

Data Index: 1084667 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.3762. Min Act: -0.0000

Data Index: 1410555 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.2591. Min Act: -0.0000

Data Index: 732915 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.3563. Min Act: -0.0000

Data Index: 839333 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 2.7939. Min Range: -2.7939

Max Act: 2.3460. Min Act: -0.0000

Data Index: 1493873 (Python Code)

Max Activating Token Index: 896