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

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

Neuron 4079 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: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0001

Data Index: 960019 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0002

Data Index: 550270 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0001

Data Index: 1330147 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0001

Data Index: 1345593 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0098. Min Act: -0.0001

Data Index: 43949 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0001

Data Index: 352805 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: -0.0001

Data Index: 206842 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0098. Min Act: -0.0001

Data Index: 922101 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0001

Data Index: 1272394 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0001

Data Index: 856996 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0001

Data Index: 942768 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0001

Data Index: 1170317 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0001

Data Index: 806155 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0001

Data Index: 713586 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0001

Data Index: 1063115 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0001

Data Index: 589637 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0001

Data Index: 277188 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0001

Data Index: 375638 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: -0.0001

Data Index: 752197 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0001

Data Index: 12482 (C4 (Web Text))

Max Activating Token Index: 838