Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.4993. Min Act: -0.1700
Data Index: 8544165 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.3112. Min Act: -0.1700
Data Index: 5929367 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.2955. Min Act: -0.1700
Data Index: 4170961 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.2798. Min Act: -0.1700
Data Index: 1632208 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.2484. Min Act: -0.1700
Data Index: 1995331 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.2484. Min Act: -0.1700
Data Index: 3132339 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.1698. Min Act: -0.1700
Data Index: 5143476 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.1698. Min Act: -0.1700
Data Index: 2714831 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.1540. Min Act: -0.1700
Data Index: 4244027 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.1383. Min Act: -0.1700
Data Index: 193142 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.1383. Min Act: -0.1700
Data Index: 4156973 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.1225. Min Act: -0.1700
Data Index: 5856044 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0910. Min Act: -0.1700
Data Index: 4062562 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0753. Min Act: -0.1700
Data Index: 2030738 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0595. Min Act: -0.1700
Data Index: 7736225 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0753. Min Act: -0.1700
Data Index: 6848533 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0595. Min Act: -0.1700
Data Index: 5395825 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0437. Min Act: -0.1700
Data Index: 1852719 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0753. Min Act: -0.1700
Data Index: 7773467 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4993. Min Range: -3.4993
Max Act: 3.0595. Min Act: -0.1700
Data Index: 1175405 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19