Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4344 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.5956. Min Act: -0.1700
Data Index: 6761011 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.5331. Min Act: -0.1700
Data Index: 6491737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.4706. Min Act: -0.1700
Data Index: 2373712 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.4706. Min Act: -0.1700
Data Index: 2366689 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.4081. Min Act: -0.1700
Data Index: 4374826 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.4706. Min Act: -0.1700
Data Index: 7162799 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.3456. Min Act: -0.1700
Data Index: 8297430 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 4150370 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2831. Min Act: -0.1700
Data Index: 5509840 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2831. Min Act: -0.1700
Data Index: 5184467 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 5474790 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 7115271 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1894. Min Act: -0.1700
Data Index: 8468366 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1581. Min Act: -0.1700
Data Index: 4378737 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1581. Min Act: -0.1700
Data Index: 4798517 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1269. Min Act: -0.1700
Data Index: 307029 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1269. Min Act: -0.1700
Data Index: 4963176 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1269. Min Act: -0.1700
Data Index: 4909509 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.0956. Min Act: -0.1700
Data Index: 1911314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.0644. Min Act: -0.1700
Data Index: 5561704 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19