Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4717 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4581. Min Range: -9.4581
Max Act: 9.4581. Min Act: -0.1700
Data Index: 5904380 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4581. Min Range: -9.4581
Max Act: 9.4581. Min Act: -0.1700
Data Index: 2447773 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4581. Min Range: -9.4581
Max Act: 9.2706. Min Act: -0.1700
Data Index: 4819089 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4581. Min Range: -9.4581
Max Act: 9.1456. Min Act: -0.1700
Data Index: 2620578 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.9581. Min Act: -0.1700
Data Index: 8649665 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.7081. Min Act: -0.1700
Data Index: 7401830 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.6456. Min Act: -0.1700
Data Index: 62943 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.5831. Min Act: -0.1700
Data Index: 941218 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.5206. Min Act: -0.1700
Data Index: 2286016 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.4581. Min Act: -0.1700
Data Index: 5426793 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.4581. Min Act: -0.1700
Data Index: 6820781 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3956. Min Act: -0.1700
Data Index: 2565994 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3956. Min Act: -0.1700
Data Index: 2590418 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3956. Min Act: -0.1700
Data Index: 4854051 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3331. Min Act: -0.1700
Data Index: 2056305 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3956. Min Act: -0.1700
Data Index: 7536833 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3331. Min Act: -0.1700
Data Index: 4721895 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3331. Min Act: -0.1700
Data Index: 5105421 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.3331. Min Act: -0.1700
Data Index: 2286007 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4581. Min Range: -9.4581
Max Act: 8.2706. Min Act: -0.1700
Data Index: 2176867 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19