Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.1910. Min Act: -0.1700
Data Index: 641314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.1910. Min Act: -0.1700
Data Index: 8640852 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.1438. Min Act: -0.1700
Data Index: 6042699 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.1123. Min Act: -0.1700
Data Index: 2465918 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0808. Min Act: -0.1700
Data Index: 6994511 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0808. Min Act: -0.1700
Data Index: 1267863 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0650. Min Act: -0.1700
Data Index: 6470338 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0492. Min Act: -0.1700
Data Index: 6325416 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0492. Min Act: -0.1700
Data Index: 4852207 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0176. Min Act: -0.1700
Data Index: 7733200 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0492. Min Act: -0.1700
Data Index: 3506021 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0334. Min Act: -0.1700
Data Index: 3345847 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0176. Min Act: -0.1700
Data Index: 1856197 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0018. Min Act: -0.1700
Data Index: 4848695 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0176. Min Act: -0.1700
Data Index: 676032 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0018. Min Act: -0.1700
Data Index: 562078 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0018. Min Act: -0.1700
Data Index: 3623137 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0018. Min Act: -0.1700
Data Index: 2872949 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1910. Min Range: -3.1910
Max Act: 2.9702. Min Act: -0.1700
Data Index: 1344631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1910. Min Range: -3.1910
Max Act: 3.0334. Min Act: -0.1700
Data Index: 4586557 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19