Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.9269. Min Act: -0.1700
Data Index: 6405536 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.8331. Min Act: -0.1700
Data Index: 1820004 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.8019. Min Act: -0.1700
Data Index: 196360 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.7081. Min Act: -0.1700
Data Index: 5777070 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.6769. Min Act: -0.1700
Data Index: 8163852 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.6456. Min Act: -0.1700
Data Index: 2821708 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5831. Min Act: -0.1700
Data Index: 3343587 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.6144. Min Act: -0.1700
Data Index: 3564192 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5831. Min Act: -0.1700
Data Index: 3567702 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5519. Min Act: -0.1700
Data Index: 5854818 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5206. Min Act: -0.1700
Data Index: 8380164 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5519. Min Act: -0.1700
Data Index: 5061598 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5206. Min Act: -0.1700
Data Index: 7543185 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5519. Min Act: -0.1700
Data Index: 1111303 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.5206. Min Act: -0.1700
Data Index: 5458296 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.4894. Min Act: -0.1700
Data Index: 4228749 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.4894. Min Act: -0.1700
Data Index: 4397987 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.4581. Min Act: -0.1700
Data Index: 7060442 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.4581. Min Act: -0.1700
Data Index: 2194664 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9269. Min Range: -5.9269
Max Act: 5.4581. Min Act: -0.1700
Data Index: 966320 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19