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

Dataset: Open Web Text

Neuron 1204 in Layer 1

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: 5.3422. Min Range: -5.3422

Max Act: 5.3422. Min Act: -0.1700

Data Index: 5489405 (Open Web Text)

Max Activating Token Index: 173

Text #1

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9776. Min Act: -0.1700

Data Index: 6701742 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9961. Min Act: -0.1700

Data Index: 5665133 (Open Web Text)

Max Activating Token Index: 71

Text #3

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9624. Min Act: -0.1700

Data Index: 256933 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9785. Min Act: -0.1700

Data Index: 5246870 (Open Web Text)

Max Activating Token Index: 320

Text #5

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9206. Min Act: -0.1700

Data Index: 2721377 (Open Web Text)

Max Activating Token Index: 665

Text #6

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8946. Min Act: -0.1700

Data Index: 3831177 (Open Web Text)

Max Activating Token Index: 183

Text #7

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8789. Min Act: -0.1700

Data Index: 7534323 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9008. Min Act: -0.1700

Data Index: 3996874 (Open Web Text)

Max Activating Token Index: 360

Text #9

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9229. Min Act: -0.1700

Data Index: 3869085 (Open Web Text)

Max Activating Token Index: 711

Text #10

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9119. Min Act: -0.1700

Data Index: 3496109 (Open Web Text)

Max Activating Token Index: 965

Text #11

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8906. Min Act: -0.1700

Data Index: 1977215 (Open Web Text)

Max Activating Token Index: 340

Text #12

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.9176. Min Act: -0.1700

Data Index: 5120940 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8985. Min Act: -0.1700

Data Index: 985547 (Open Web Text)

Max Activating Token Index: 245

Text #14

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8835. Min Act: -0.1700

Data Index: 660648 (Open Web Text)

Max Activating Token Index: 81

Text #15

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8650. Min Act: -0.1700

Data Index: 7666587 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8597. Min Act: -0.1700

Data Index: 175479 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8885. Min Act: -0.1700

Data Index: 6951763 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8714. Min Act: -0.1700

Data Index: 4236979 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 5.3422. Min Range: -5.3422

Max Act: 4.8561. Min Act: -0.1700

Data Index: 3477720 (Open Web Text)

Max Activating Token Index: 196