Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.8081. Min Act: -0.1700
Data Index: 4571747 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.7612. Min Act: -0.1700
Data Index: 1626595 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6986. Min Act: -0.1700
Data Index: 7707198 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6830. Min Act: -0.1700
Data Index: 2463649 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6830. Min Act: -0.1700
Data Index: 2611871 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6673. Min Act: -0.1700
Data Index: 2873623 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6361. Min Act: -0.1700
Data Index: 4043109 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6517. Min Act: -0.1700
Data Index: 1045560 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6361. Min Act: -0.1700
Data Index: 482636 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6048. Min Act: -0.1700
Data Index: 4091946 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6048. Min Act: -0.1700
Data Index: 346734 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5891. Min Act: -0.1700
Data Index: 7231131 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5735. Min Act: -0.1700
Data Index: 4932601 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5735. Min Act: -0.1700
Data Index: 442633 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5578. Min Act: -0.1700
Data Index: 1908695 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5735. Min Act: -0.1700
Data Index: 4609679 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5421. Min Act: -0.1700
Data Index: 4393087 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5265. Min Act: -0.1700
Data Index: 7379960 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5108. Min Act: -0.1700
Data Index: 3782696 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5265. Min Act: -0.1700
Data Index: 4721675 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19