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

Dataset: Open Web Text

Neuron 1839 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: 5.1956. Min Range: -5.1956

Max Act: 5.1956. Min Act: -0.1700

Data Index: 7399217 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.1865. Min Act: -0.1700

Data Index: 6380026 (Open Web Text)

Max Activating Token Index: 692

Text #2

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.1221. Min Act: -0.1700

Data Index: 324183 (Open Web Text)

Max Activating Token Index: 793

Text #3

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0880. Min Act: -0.1700

Data Index: 5191323 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0574. Min Act: -0.1700

Data Index: 3525084 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0562. Min Act: -0.1700

Data Index: 4685219 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9787. Min Act: -0.1700

Data Index: 7092387 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9721. Min Act: -0.1700

Data Index: 2948176 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9923. Min Act: -0.1700

Data Index: 2536669 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9607. Min Act: -0.1700

Data Index: 6933106 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9570. Min Act: -0.1700

Data Index: 5190366 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9409. Min Act: -0.1700

Data Index: 5997796 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9701. Min Act: -0.1700

Data Index: 7680533 (Open Web Text)

Max Activating Token Index: 533

Text #13

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8868. Min Act: -0.1700

Data Index: 1158217 (Open Web Text)

Max Activating Token Index: 421

Text #14

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8978. Min Act: -0.1700

Data Index: 7772140 (Open Web Text)

Max Activating Token Index: 518

Text #15

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8628. Min Act: -0.1700

Data Index: 2372875 (Open Web Text)

Max Activating Token Index: 503

Text #16

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8891. Min Act: -0.1700

Data Index: 494130 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8995. Min Act: -0.1700

Data Index: 5900518 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8460. Min Act: -0.1700

Data Index: 620204 (Open Web Text)

Max Activating Token Index: 600

Text #19

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8233. Min Act: -0.1700

Data Index: 1569671 (Open Web Text)

Max Activating Token Index: 932