Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1058 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.8135. Min Act: -0.1699

Data Index: 4124838 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7819. Min Act: -0.1700

Data Index: 7705130 (Open Web Text)

Max Activating Token Index: 295

Text #2

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7160. Min Act: -0.1700

Data Index: 6154410 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7077. Min Act: -0.1700

Data Index: 3470796 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7035. Min Act: -0.1700

Data Index: 710417 (Open Web Text)

Max Activating Token Index: 386

Text #5

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6981. Min Act: -0.1700

Data Index: 5066758 (Open Web Text)

Max Activating Token Index: 208

Text #6

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6850. Min Act: -0.1700

Data Index: 3996757 (Open Web Text)

Max Activating Token Index: 466

Text #7

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6712. Min Act: -0.1700

Data Index: 298090 (Open Web Text)

Max Activating Token Index: 418

Text #8

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6631. Min Act: -0.1700

Data Index: 4680058 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6656. Min Act: -0.1700

Data Index: 499455 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6726. Min Act: -0.1697

Data Index: 7205141 (Open Web Text)

Max Activating Token Index: 528

Text #11

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6577. Min Act: -0.1700

Data Index: 3512581 (Open Web Text)

Max Activating Token Index: 191

Text #12

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6559. Min Act: -0.1700

Data Index: 8756794 (Open Web Text)

Max Activating Token Index: 621

Text #13

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6617. Min Act: -0.1700

Data Index: 2870335 (Open Web Text)

Max Activating Token Index: 270

Text #14

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6579. Min Act: -0.1699

Data Index: 2317211 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6643. Min Act: -0.1700

Data Index: 6398884 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6492. Min Act: -0.1700

Data Index: 31231 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6342. Min Act: -0.1700

Data Index: 12240 (Open Web Text)

Max Activating Token Index: 97

Text #18

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6276. Min Act: -0.1700

Data Index: 4114406 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6357. Min Act: -0.1700

Data Index: 1931437 (Open Web Text)

Max Activating Token Index: 102