Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.5775. Min Act: -0.1700
Data Index: 6871109 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.4837. Min Act: -0.1700
Data Index: 6024525 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.4837. Min Act: -0.1700
Data Index: 8777638 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.4525. Min Act: -0.1700
Data Index: 2293749 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.4525. Min Act: -0.1700
Data Index: 3210860 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.4212. Min Act: -0.1700
Data Index: 3620230 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.3900. Min Act: -0.1700
Data Index: 3193752 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.3587. Min Act: -0.1700
Data Index: 873196 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2962. Min Act: -0.1700
Data Index: 863351 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.3275. Min Act: -0.1700
Data Index: 5520682 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2962. Min Act: -0.1700
Data Index: 2197661 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2962. Min Act: -0.1700
Data Index: 3970412 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2962. Min Act: -0.1700
Data Index: 8196650 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2962. Min Act: -0.1700
Data Index: 4706291 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2962. Min Act: -0.1700
Data Index: 2960000 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2962. Min Act: -0.1700
Data Index: 7266899 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2650. Min Act: -0.1700
Data Index: 4785816 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2337. Min Act: -0.1700
Data Index: 4734978 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2337. Min Act: -0.1700
Data Index: 997845 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5775. Min Range: -6.5775
Max Act: 6.2337. Min Act: -0.1700
Data Index: 4920310 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19