Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.5055. Min Act: -0.1700
Data Index: 4418567 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.4430. Min Act: -0.1700
Data Index: 386946 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.4117. Min Act: -0.1700
Data Index: 2779678 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.4117. Min Act: -0.1700
Data Index: 7988998 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.4117. Min Act: -0.1700
Data Index: 3665152 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.4117. Min Act: -0.1700
Data Index: 349598 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.3805. Min Act: -0.1700
Data Index: 7124719 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.3180. Min Act: -0.1700
Data Index: 4476782 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.2867. Min Act: -0.1700
Data Index: 2954357 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.2242. Min Act: -0.1700
Data Index: 198981 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.2242. Min Act: -0.1700
Data Index: 346834 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1930. Min Act: -0.1700
Data Index: 7817784 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1930. Min Act: -0.1700
Data Index: 669132 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1930. Min Act: -0.1700
Data Index: 8722132 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1930. Min Act: -0.1700
Data Index: 213578 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1305. Min Act: -0.1700
Data Index: 8068820 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1617. Min Act: -0.1700
Data Index: 352117 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1617. Min Act: -0.1700
Data Index: 2738884 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1305. Min Act: -0.1700
Data Index: 5252165 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5055. Min Range: -6.5055
Max Act: 6.1305. Min Act: -0.1700
Data Index: 3722227 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19