Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.4838. Min Act: -0.1700
Data Index: 8166306 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.4525. Min Act: -0.1700
Data Index: 8109343 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.4525. Min Act: -0.1700
Data Index: 7724662 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1713. Min Act: -0.1700
Data Index: 3869006 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1713. Min Act: -0.1700
Data Index: 8532369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1400. Min Act: -0.1700
Data Index: 5568794 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1400. Min Act: -0.1700
Data Index: 8447890 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0463. Min Act: -0.1700
Data Index: 5711036 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0150. Min Act: -0.1700
Data Index: 7803394 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9525. Min Act: -0.1700
Data Index: 8390764 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9838. Min Act: -0.1700
Data Index: 2458780 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0150. Min Act: -0.1700
Data Index: 212135 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0150. Min Act: -0.1700
Data Index: 3400388 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9525. Min Act: -0.1700
Data Index: 2711077 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9838. Min Act: -0.1700
Data Index: 8819562 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9213. Min Act: -0.1700
Data Index: 6587554 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9838. Min Act: -0.1700
Data Index: 7803390 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9525. Min Act: -0.1700
Data Index: 2586738 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9213. Min Act: -0.1700
Data Index: 7803389 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4838. Min Range: -5.4838
Max Act: 4.9525. Min Act: -0.1700
Data Index: 4073468 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19