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

Dataset: Open Web Text

Neuron 178 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: 2.9341. Min Range: -2.9341

Max Act: 2.9340. Min Act: -0.1700

Data Index: 4082350 (Open Web Text)

Max Activating Token Index: 888

Text #1

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.9341. Min Act: -0.1700

Data Index: 5426712 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.9271. Min Act: -0.1700

Data Index: 7009369 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.9203. Min Act: -0.1700

Data Index: 8679400 (Open Web Text)

Max Activating Token Index: 274

Text #4

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8927. Min Act: -0.1700

Data Index: 5079221 (Open Web Text)

Max Activating Token Index: 124

Text #5

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8945. Min Act: -0.1700

Data Index: 4438104 (Open Web Text)

Max Activating Token Index: 196

Text #6

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8884. Min Act: -0.1700

Data Index: 7512929 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8963. Min Act: -0.1700

Data Index: 510612 (Open Web Text)

Max Activating Token Index: 583

Text #8

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8932. Min Act: -0.1700

Data Index: 6728200 (Open Web Text)

Max Activating Token Index: 1003

Text #9

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8887. Min Act: -0.1700

Data Index: 3719222 (Open Web Text)

Max Activating Token Index: 326

Text #10

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8786. Min Act: -0.1700

Data Index: 3688104 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8824. Min Act: -0.1700

Data Index: 4082349 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8671. Min Act: -0.1700

Data Index: 5307819 (Open Web Text)

Max Activating Token Index: 663

Text #13

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8763. Min Act: -0.1700

Data Index: 157646 (Open Web Text)

Max Activating Token Index: 971

Text #14

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8795. Min Act: -0.1700

Data Index: 1856051 (Open Web Text)

Max Activating Token Index: 253

Text #15

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8836. Min Act: -0.1700

Data Index: 318352 (Open Web Text)

Max Activating Token Index: 969

Text #16

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8662. Min Act: -0.1700

Data Index: 1512044 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8752. Min Act: -0.1700

Data Index: 4950666 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8654. Min Act: -0.1700

Data Index: 1523538 (Open Web Text)

Max Activating Token Index: 742

Text #19

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8738. Min Act: -0.1700

Data Index: 1640611 (Open Web Text)

Max Activating Token Index: 58