Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1441. Min Range: -3.1441
Max Act: 3.1441. Min Act: -0.1700
Data Index: 459314 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.9863. Min Act: -0.1700
Data Index: 8347370 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.9388. Min Act: -0.1700
Data Index: 3251633 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.9547. Min Act: -0.1700
Data Index: 4308952 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.9547. Min Act: -0.1700
Data Index: 3974470 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.9230. Min Act: -0.1700
Data Index: 8710140 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.8754. Min Act: -0.1700
Data Index: 7041654 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.8913. Min Act: -0.1700
Data Index: 1598926 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.8913. Min Act: -0.1700
Data Index: 2171451 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.9071. Min Act: -0.1700
Data Index: 2798192 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.9071. Min Act: -0.1700
Data Index: 8574201 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.8754. Min Act: -0.1700
Data Index: 4692983 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.8437. Min Act: -0.1700
Data Index: 4187480 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.7800. Min Act: -0.1700
Data Index: 6185053 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.7800. Min Act: -0.1700
Data Index: 1673076 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.7640. Min Act: -0.1700
Data Index: 7338315 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.7640. Min Act: -0.1700
Data Index: 4660848 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.7321. Min Act: -0.1700
Data Index: 2928883 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.7481. Min Act: -0.1700
Data Index: 4013982 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1441. Min Range: -3.1441
Max Act: 2.7481. Min Act: -0.1700
Data Index: 2359812 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19