Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 623 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4452. Min Range: -6.4452
Max Act: 6.4452. Min Act: -0.1700
Data Index: 3625508 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4452. Min Range: -6.4452
Max Act: 6.2264. Min Act: -0.1700
Data Index: 4848985 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4452. Min Range: -6.4452
Max Act: 6.2577. Min Act: -0.1700
Data Index: 3526745 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4452. Min Range: -6.4452
Max Act: 6.1952. Min Act: -0.1700
Data Index: 2188418 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4452. Min Range: -6.4452
Max Act: 6.1014. Min Act: -0.1700
Data Index: 7820279 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4452. Min Range: -6.4452
Max Act: 6.0389. Min Act: -0.1700
Data Index: 4233972 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.9764. Min Act: -0.1700
Data Index: 6410507 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.9764. Min Act: -0.1700
Data Index: 6923413 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.9452. Min Act: -0.1700
Data Index: 7912251 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.9139. Min Act: -0.1700
Data Index: 8805667 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8827. Min Act: -0.1700
Data Index: 5971056 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.9139. Min Act: -0.1700
Data Index: 5286474 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8827. Min Act: -0.1700
Data Index: 1718011 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8514. Min Act: -0.1700
Data Index: 1696597 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8827. Min Act: -0.1700
Data Index: 8240293 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8514. Min Act: -0.1700
Data Index: 5723764 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8514. Min Act: -0.1700
Data Index: 8259728 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8514. Min Act: -0.1700
Data Index: 7089294 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.9139. Min Act: -0.1700
Data Index: 6703590 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4452. Min Range: -6.4452
Max Act: 5.8827. Min Act: -0.1700
Data Index: 5681722 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19