Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1682. Min Range: -3.1682
Max Act: 3.1682. Min Act: -0.1700
Data Index: 7829295 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1682. Min Range: -3.1682
Max Act: 3.0737. Min Act: -0.1700
Data Index: 34300 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1682. Min Range: -3.1682
Max Act: 3.0895. Min Act: -0.1700
Data Index: 6482589 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1682. Min Range: -3.1682
Max Act: 3.0579. Min Act: -0.1700
Data Index: 1787488 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1682. Min Range: -3.1682
Max Act: 3.0105. Min Act: -0.1700
Data Index: 2840559 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9789. Min Act: -0.1700
Data Index: 4603140 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9631. Min Act: -0.1700
Data Index: 4233518 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1682. Min Range: -3.1682
Max Act: 3.0105. Min Act: -0.1700
Data Index: 2822066 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9789. Min Act: -0.1700
Data Index: 2250972 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9631. Min Act: -0.1700
Data Index: 4898991 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9315. Min Act: -0.1700
Data Index: 5049113 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9315. Min Act: -0.1700
Data Index: 6525806 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9631. Min Act: -0.1700
Data Index: 517815 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9156. Min Act: -0.1700
Data Index: 6870965 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9156. Min Act: -0.1700
Data Index: 1584524 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.8839. Min Act: -0.1700
Data Index: 5270861 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9473. Min Act: -0.1700
Data Index: 5049112 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.8839. Min Act: -0.1700
Data Index: 1102425 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.8998. Min Act: -0.1700
Data Index: 5171996 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1682. Min Range: -3.1682
Max Act: 2.9156. Min Act: -0.1700
Data Index: 5335096 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19