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

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

Neuron 1965 in Layer 0

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: 0.4489. Min Range: -0.4489

Max Act: 0.4489. Min Act: -0.0001

Data Index: 1510667 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4424. Min Act: -0.0002

Data Index: 1482313 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1371398 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4275. Min Act: -0.0002

Data Index: 1447540 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1562829 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4227. Min Act: -0.0002

Data Index: 1470097 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4185. Min Act: -0.0001

Data Index: 1650200 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1600475 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4176. Min Act: -0.0001

Data Index: 1481547 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4066. Min Act: -0.0001

Data Index: 1545243 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4082. Min Act: -0.0001

Data Index: 1449937 (Python Code)

Max Activating Token Index: 343

Text #11

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4055. Min Act: -0.0001

Data Index: 1584789 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1645118 (Python Code)

Max Activating Token Index: 686

Text #13

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4095. Min Act: -0.0001

Data Index: 1360320 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4028. Min Act: -0.0002

Data Index: 1586040 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1471051 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4074. Min Act: -0.0001

Data Index: 1501525 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4016. Min Act: -0.0001

Data Index: 1503983 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.4098. Min Act: -0.0001

Data Index: 1637492 (Python Code)

Max Activating Token Index: 278

Text #19

Max Range: 0.4489. Min Range: -0.4489

Max Act: 0.3955. Min Act: -0.0001

Data Index: 1483354 (Python Code)

Max Activating Token Index: 463