Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.7963. Min Act: -0.1700
Data Index: 2371405 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.6400. Min Act: -0.1700
Data Index: 4541525 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.6088. Min Act: -0.1700
Data Index: 1175269 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.6088. Min Act: -0.1700
Data Index: 4955380 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.5775. Min Act: -0.1700
Data Index: 7164542 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.5463. Min Act: -0.1700
Data Index: 933517 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.5463. Min Act: -0.1700
Data Index: 7793916 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.5463. Min Act: -0.1700
Data Index: 7933108 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.5150. Min Act: -0.1700
Data Index: 7157980 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.5150. Min Act: -0.1700
Data Index: 949938 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.5150. Min Act: -0.1700
Data Index: 2679176 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4838. Min Act: -0.1700
Data Index: 6394118 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4525. Min Act: -0.1700
Data Index: 2427366 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4838. Min Act: -0.1700
Data Index: 1123268 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4838. Min Act: -0.1700
Data Index: 8441726 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4525. Min Act: -0.1700
Data Index: 7673082 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4525. Min Act: -0.1700
Data Index: 8161241 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4525. Min Act: -0.1700
Data Index: 1534963 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4525. Min Act: -0.1700
Data Index: 2371412 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7963. Min Range: -4.7963
Max Act: 4.4213. Min Act: -0.1700
Data Index: 5425923 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19