Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1670 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.1105. Min Range: -7.1105

Max Act: 7.1105. Min Act: -0.1700

Data Index: 832089 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 7.1105. Min Range: -7.1105

Max Act: 7.0480. Min Act: -0.1700

Data Index: 397482 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 7.1105. Min Range: -7.1105

Max Act: 7.0168. Min Act: -0.1700

Data Index: 840481 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.7668. Min Act: -0.1700

Data Index: 570852 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.7355. Min Act: -0.1700

Data Index: 1214579 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.6105. Min Act: -0.1700

Data Index: 615579 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.7043. Min Act: -0.1700

Data Index: 58899 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.5793. Min Act: -0.1700

Data Index: 134302 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.5480. Min Act: -0.1700

Data Index: 165892 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.5168. Min Act: -0.1700

Data Index: 1267978 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.4855. Min Act: -0.1700

Data Index: 619842 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.5480. Min Act: -0.1700

Data Index: 445229 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.4543. Min Act: -0.1700

Data Index: 511938 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.5168. Min Act: -0.1700

Data Index: 1142295 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.4543. Min Act: -0.1700

Data Index: 89549 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.3605. Min Act: -0.1700

Data Index: 311129 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.4230. Min Act: -0.1700

Data Index: 688007 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.4230. Min Act: -0.1700

Data Index: 34689 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.4230. Min Act: -0.1700

Data Index: 356040 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 7.1105. Min Range: -7.1105

Max Act: 6.3605. Min Act: -0.1700

Data Index: 188563 (C4 (Web Text))

Max Activating Token Index: 242