Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0721. Min Range: -4.0721
Max Act: 4.0721. Min Act: -0.1700
Data Index: 3701249 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0721. Min Range: -4.0721
Max Act: 4.0409. Min Act: -0.1700
Data Index: 1384133 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.9940. Min Act: -0.1700
Data Index: 4801025 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.9002. Min Act: -0.1700
Data Index: 3469844 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.9002. Min Act: -0.1700
Data Index: 5545419 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.9002. Min Act: -0.1700
Data Index: 5881154 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.8533. Min Act: -0.1700
Data Index: 6796793 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.8533. Min Act: -0.1700
Data Index: 3904201 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.8220. Min Act: -0.1700
Data Index: 1170139 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.8220. Min Act: -0.1700
Data Index: 2722612 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.8064. Min Act: -0.1700
Data Index: 844751 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.8064. Min Act: -0.1700
Data Index: 7323086 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.7908. Min Act: -0.1700
Data Index: 2084116 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.7908. Min Act: -0.1700
Data Index: 8332856 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.7908. Min Act: -0.1700
Data Index: 1592743 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.7908. Min Act: -0.1700
Data Index: 1234871 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.7751. Min Act: -0.1700
Data Index: 6212767 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.7908. Min Act: -0.1700
Data Index: 6613417 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.8064. Min Act: -0.1700
Data Index: 3817442 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0721. Min Range: -4.0721
Max Act: 3.7751. Min Act: -0.1700
Data Index: 2337800 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19