Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2811. Min Act: -0.1700
Data Index: 8006828 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2811. Min Act: -0.1700
Data Index: 809849 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2497. Min Act: -0.1700
Data Index: 2829446 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2026. Min Act: -0.1700
Data Index: 3467959 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2183. Min Act: -0.1700
Data Index: 599892 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2340. Min Act: -0.1700
Data Index: 4319783 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2183. Min Act: -0.1700
Data Index: 6648702 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2026. Min Act: -0.1700
Data Index: 1564650 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2026. Min Act: -0.1700
Data Index: 314256 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2026. Min Act: -0.1700
Data Index: 6251250 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1868. Min Act: -0.1700
Data Index: 3240876 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1711. Min Act: -0.1700
Data Index: 3987625 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.2026. Min Act: -0.1700
Data Index: 8767316 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1868. Min Act: -0.1700
Data Index: 2584575 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1554. Min Act: -0.1700
Data Index: 7720831 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1396. Min Act: -0.1700
Data Index: 6322395 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1554. Min Act: -0.1700
Data Index: 4149810 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1081. Min Act: -0.1700
Data Index: 8435799 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1868. Min Act: -0.1700
Data Index: 309174 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2811. Min Range: -3.2811
Max Act: 3.1554. Min Act: -0.1700
Data Index: 2538304 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19