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

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

Neuron 706 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.6134. Min Act: -0.0002

Data Index: 1064551 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.6011. Min Act: -0.0002

Data Index: 1356998 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.5216. Min Act: -0.0002

Data Index: 814869 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.5087. Min Act: -0.0002

Data Index: 569739 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.5119. Min Act: -0.0002

Data Index: 292858 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4836. Min Act: -0.0002

Data Index: 732297 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4501. Min Act: -0.0002

Data Index: 950318 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4127. Min Act: -0.0002

Data Index: 410693 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4127. Min Act: -0.0002

Data Index: 384063 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4279. Min Act: -0.0002

Data Index: 274402 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4199. Min Act: -0.0002

Data Index: 679916 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4043. Min Act: -0.0002

Data Index: 989094 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.3950. Min Act: -0.0002

Data Index: 1310975 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4006. Min Act: -0.0002

Data Index: 1225580 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4371. Min Act: -0.0002

Data Index: 32398 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4107. Min Act: -0.0002

Data Index: 61254 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.4071. Min Act: -0.0002

Data Index: 1042575 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.3825. Min Act: -0.0002

Data Index: 714216 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.3555. Min Act: -0.0002

Data Index: 177738 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.6134. Min Range: -1.6134

Max Act: 1.3713. Min Act: -0.0002

Data Index: 336828 (C4 (Web Text))

Max Activating Token Index: 168