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

Dataset: Open Web Text

Neuron 1927 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: 2.1145. Min Range: -2.1145

Max Act: 2.1145. Min Act: -0.1700

Data Index: 4572160 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.0985. Min Act: -0.1700

Data Index: 202144 (Open Web Text)

Max Activating Token Index: 458

Text #2

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.0437. Min Act: -0.1700

Data Index: 2119776 (Open Web Text)

Max Activating Token Index: 186

Text #3

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.0346. Min Act: -0.1700

Data Index: 7919120 (Open Web Text)

Max Activating Token Index: 246

Text #4

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.0211. Min Act: -0.1700

Data Index: 5432657 (Open Web Text)

Max Activating Token Index: 164

Text #5

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.0130. Min Act: -0.1700

Data Index: 6685248 (Open Web Text)

Max Activating Token Index: 68

Text #6

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.0052. Min Act: -0.1700

Data Index: 1895715 (Open Web Text)

Max Activating Token Index: 534

Text #7

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9836. Min Act: -0.1700

Data Index: 3052453 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9994. Min Act: -0.1700

Data Index: 7960737 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9983. Min Act: -0.1700

Data Index: 6160402 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.0060. Min Act: -0.1700

Data Index: 2460075 (Open Web Text)

Max Activating Token Index: 164

Text #11

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9939. Min Act: -0.1700

Data Index: 1796497 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9739. Min Act: -0.1700

Data Index: 4668261 (Open Web Text)

Max Activating Token Index: 960

Text #13

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9788. Min Act: -0.1700

Data Index: 1284853 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9750. Min Act: -0.1700

Data Index: 3920089 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9862. Min Act: -0.1699

Data Index: 8344567 (Open Web Text)

Max Activating Token Index: 196

Text #16

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9821. Min Act: -0.1700

Data Index: 2948950 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9702. Min Act: -0.1700

Data Index: 1630975 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9738. Min Act: -0.1700

Data Index: 8524494 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.9749. Min Act: -0.1700

Data Index: 3615916 (Open Web Text)

Max Activating Token Index: 128