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

Dataset: Open Web Text

Neuron 170 in Layer 3

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: 8.3181. Min Range: -8.3181

Max Act: 8.2538. Min Act: -0.1700

Data Index: 5973493 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 8.3181. Min Range: -8.3181

Max Act: 8.3181. Min Act: -0.1700

Data Index: 5667518 (Open Web Text)

Max Activating Token Index: 933

Text #2

Max Range: 8.3181. Min Range: -8.3181

Max Act: 8.0303. Min Act: -0.1700

Data Index: 418233 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 8.3181. Min Range: -8.3181

Max Act: 8.0165. Min Act: -0.1700

Data Index: 7324978 (Open Web Text)

Max Activating Token Index: 121

Text #4

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.9166. Min Act: -0.1700

Data Index: 1782589 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.8207. Min Act: -0.1700

Data Index: 3617261 (Open Web Text)

Max Activating Token Index: 998

Text #6

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7994. Min Act: -0.1700

Data Index: 7679238 (Open Web Text)

Max Activating Token Index: 887

Text #7

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.8383. Min Act: -0.1700

Data Index: 3667386 (Open Web Text)

Max Activating Token Index: 325

Text #8

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7711. Min Act: -0.1700

Data Index: 3617276 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.8819. Min Act: -0.1700

Data Index: 3633106 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7589. Min Act: -0.1700

Data Index: 5101342 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7023. Min Act: -0.1700

Data Index: 8232973 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7296. Min Act: -0.1700

Data Index: 552744 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.6024. Min Act: -0.1700

Data Index: 199219 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.6155. Min Act: -0.1700

Data Index: 5154919 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7732. Min Act: -0.1700

Data Index: 8253729 (Open Web Text)

Max Activating Token Index: 339

Text #16

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7336. Min Act: -0.1700

Data Index: 4294256 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.7323. Min Act: -0.1700

Data Index: 4817367 (Open Web Text)

Max Activating Token Index: 867

Text #18

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.5393. Min Act: -0.1700

Data Index: 5466003 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 8.3181. Min Range: -8.3181

Max Act: 7.6425. Min Act: -0.1700

Data Index: 496478 (Open Web Text)

Max Activating Token Index: 120