Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.8662. Min Act: -0.1700
Data Index: 4401137 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.5850. Min Act: -0.1700
Data Index: 2370978 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.4912. Min Act: -0.1700
Data Index: 4369706 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.4287. Min Act: -0.1700
Data Index: 854922 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.3350. Min Act: -0.1700
Data Index: 673385 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.3037. Min Act: -0.1700
Data Index: 121193 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.3037. Min Act: -0.1700
Data Index: 8095647 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.2725. Min Act: -0.1700
Data Index: 1087004 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.2725. Min Act: -0.1700
Data Index: 2270122 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.2412. Min Act: -0.1700
Data Index: 5444124 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.2100. Min Act: -0.1700
Data Index: 894576 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.1787. Min Act: -0.1700
Data Index: 8372729 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.1787. Min Act: -0.1700
Data Index: 2322584 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.1787. Min Act: -0.1700
Data Index: 1172053 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.1162. Min Act: -0.1700
Data Index: 5507491 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.1162. Min Act: -0.1700
Data Index: 4011962 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.0850. Min Act: -0.1700
Data Index: 6916488 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.0850. Min Act: -0.1700
Data Index: 8579885 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.0850. Min Act: -0.1700
Data Index: 7345492 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8662. Min Range: -7.8662
Max Act: 7.0850. Min Act: -0.1700
Data Index: 6404443 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19