Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1310 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1323796 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4979. Min Act: -0.1700

Data Index: 271733 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.5038. Min Act: -0.1700

Data Index: 910160 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.5011. Min Act: -0.1700

Data Index: 1022475 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4884. Min Act: -0.1697

Data Index: 586719 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4830. Min Act: -0.1700

Data Index: 946556 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4712. Min Act: -0.1700

Data Index: 526020 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4708. Min Act: -0.1699

Data Index: 806292 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4377. Min Act: -0.1700

Data Index: 988729 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4535. Min Act: -0.1700

Data Index: 278675 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4637. Min Act: -0.1700

Data Index: 1039089 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4540. Min Act: -0.1700

Data Index: 768004 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4510. Min Act: -0.1700

Data Index: 191933 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4587. Min Act: -0.1688

Data Index: 919553 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4141. Min Act: -0.1700

Data Index: 1340942 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4245. Min Act: -0.1697

Data Index: 672164 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4143. Min Act: -0.1691

Data Index: 996199 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.4058. Min Act: -0.1700

Data Index: 925626 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.3980. Min Act: -0.1700

Data Index: 858385 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 3.5105. Min Range: -3.5105

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1128403 (C4 (Web Text))

Max Activating Token Index: 582