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

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

Neuron 615 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: 0.6933. Min Range: -0.6933

Max Act: 0.6933. Min Act: -0.0002

Data Index: 664548 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6697. Min Act: -0.0002

Data Index: 116001 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6739. Min Act: -0.0003

Data Index: 1138924 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6545. Min Act: -0.0002

Data Index: 58017 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6554. Min Act: -0.0002

Data Index: 69734 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6472. Min Act: -0.0002

Data Index: 1293200 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6417. Min Act: -0.0003

Data Index: 467357 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6074. Min Act: -0.0002

Data Index: 918576 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6098. Min Act: -0.0002

Data Index: 1142493 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6264. Min Act: -0.0002

Data Index: 393939 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6099. Min Act: -0.0003

Data Index: 1102878 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6166. Min Act: -0.0003

Data Index: 395749 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6173. Min Act: -0.0002

Data Index: 667741 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5928. Min Act: -0.0002

Data Index: 1121533 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6058. Min Act: -0.0002

Data Index: 150906 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6003. Min Act: -0.0002

Data Index: 558300 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5998. Min Act: -0.0003

Data Index: 661799 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5986. Min Act: -0.0002

Data Index: 309028 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6064. Min Act: -0.0002

Data Index: 1127808 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6005. Min Act: -0.0002

Data Index: 597000 (C4 (Web Text))

Max Activating Token Index: 794