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

Dataset: Open Web Text

Neuron 1608 in Layer 6

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: 3.0774. Min Range: -3.0774

Max Act: 3.0774. Min Act: -0.1700

Data Index: 1199524 (Open Web Text)

Max Activating Token Index: 792

Text #1

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.9730. Min Act: -0.1700

Data Index: 2515069 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8989. Min Act: -0.1700

Data Index: 3369281 (Open Web Text)

Max Activating Token Index: 435

Text #3

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.9097. Min Act: -0.1700

Data Index: 8250163 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.9060. Min Act: -0.1700

Data Index: 2230146 (Open Web Text)

Max Activating Token Index: 1009

Text #5

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8846. Min Act: -0.1700

Data Index: 2954043 (Open Web Text)

Max Activating Token Index: 101

Text #6

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8701. Min Act: -0.1700

Data Index: 5561610 (Open Web Text)

Max Activating Token Index: 668

Text #7

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8623. Min Act: -0.1700

Data Index: 8452142 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8793. Min Act: -0.1700

Data Index: 5175230 (Open Web Text)

Max Activating Token Index: 502

Text #9

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8452. Min Act: -0.1700

Data Index: 1104253 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8393. Min Act: -0.1700

Data Index: 6789461 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8487. Min Act: -0.1700

Data Index: 3221192 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8232. Min Act: -0.1700

Data Index: 5865793 (Open Web Text)

Max Activating Token Index: 611

Text #13

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8301. Min Act: -0.1700

Data Index: 5711216 (Open Web Text)

Max Activating Token Index: 348

Text #14

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.7992. Min Act: -0.1700

Data Index: 4705946 (Open Web Text)

Max Activating Token Index: 538

Text #15

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8414. Min Act: -0.1700

Data Index: 8246083 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8417. Min Act: -0.1700

Data Index: 2266722 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8232. Min Act: -0.1700

Data Index: 8761436 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8051. Min Act: -0.1700

Data Index: 366703 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 3.0774. Min Range: -3.0774

Max Act: 2.8460. Min Act: -0.1700

Data Index: 4928889 (Open Web Text)

Max Activating Token Index: 202