Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 412 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.2679. Min Act: -0.1700
Data Index: 8590432 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.1736. Min Act: -0.1700
Data Index: 5439100 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.1736. Min Act: -0.1700
Data Index: 7099788 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.1263. Min Act: -0.1700
Data Index: 2162649 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.1263. Min Act: -0.1700
Data Index: 8701674 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.0633. Min Act: -0.1700
Data Index: 7641634 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.0633. Min Act: -0.1700
Data Index: 7144952 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.0317. Min Act: -0.1700
Data Index: 2332377 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.0317. Min Act: -0.1700
Data Index: 5099461 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.0001. Min Act: -0.1700
Data Index: 2355735 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.0001. Min Act: -0.1700
Data Index: 1002756 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9843. Min Act: -0.1700
Data Index: 7925581 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9843. Min Act: -0.1700
Data Index: 7867891 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9843. Min Act: -0.1700
Data Index: 4725981 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9685. Min Act: -0.1700
Data Index: 4683718 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2679. Min Range: -3.2679
Max Act: 3.0159. Min Act: -0.1700
Data Index: 1392723 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9685. Min Act: -0.1700
Data Index: 4750222 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9843. Min Act: -0.1700
Data Index: 1220056 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9685. Min Act: -0.1700
Data Index: 3759089 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2679. Min Range: -3.2679
Max Act: 2.9527. Min Act: -0.1700
Data Index: 538450 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19