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

Dataset: Open Web Text

Neuron 1800 in Layer 0

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: 2.9366. Min Range: -2.9366

Max Act: 2.9366. Min Act: -0.1700

Data Index: 1713574 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.9156. Min Act: -0.1700

Data Index: 2296437 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.9237. Min Act: -0.1700

Data Index: 4211468 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.9122. Min Act: -0.1700

Data Index: 6990641 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8990. Min Act: -0.1700

Data Index: 6735071 (Open Web Text)

Max Activating Token Index: 77

Text #5

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8676. Min Act: -0.1700

Data Index: 5330359 (Open Web Text)

Max Activating Token Index: 67

Text #6

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8656. Min Act: -0.1700

Data Index: 6988763 (Open Web Text)

Max Activating Token Index: 65

Text #7

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8820. Min Act: -0.1700

Data Index: 6350455 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8755. Min Act: -0.1700

Data Index: 5526699 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8775. Min Act: -0.1700

Data Index: 5526136 (Open Web Text)

Max Activating Token Index: 562

Text #10

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8582. Min Act: -0.1700

Data Index: 8191574 (Open Web Text)

Max Activating Token Index: 45

Text #11

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8475. Min Act: -0.1700

Data Index: 4292073 (Open Web Text)

Max Activating Token Index: 510

Text #12

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8495. Min Act: -0.1700

Data Index: 390191 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8502. Min Act: -0.1700

Data Index: 7094103 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8507. Min Act: -0.1700

Data Index: 6378823 (Open Web Text)

Max Activating Token Index: 282

Text #15

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8360. Min Act: -0.1700

Data Index: 340515 (Open Web Text)

Max Activating Token Index: 74

Text #16

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8358. Min Act: -0.1700

Data Index: 657452 (Open Web Text)

Max Activating Token Index: 160

Text #17

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8486. Min Act: -0.1700

Data Index: 776157 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8358. Min Act: -0.1700

Data Index: 4997672 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 2.9366. Min Range: -2.9366

Max Act: 2.8467. Min Act: -0.1700

Data Index: 5093927 (Open Web Text)

Max Activating Token Index: 616