Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.4745. Min Act: -0.1700
Data Index: 7603189 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.3807. Min Act: -0.1700
Data Index: 6352678 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.3495. Min Act: -0.1700
Data Index: 1865345 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.3495. Min Act: -0.1700
Data Index: 1826915 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.3495. Min Act: -0.1700
Data Index: 3967460 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.3495. Min Act: -0.1700
Data Index: 7821914 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2870. Min Act: -0.1700
Data Index: 2268254 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2557. Min Act: -0.1700
Data Index: 3646693 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2870. Min Act: -0.1700
Data Index: 506532 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2557. Min Act: -0.1700
Data Index: 3802779 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2557. Min Act: -0.1700
Data Index: 3637706 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2557. Min Act: -0.1700
Data Index: 970231 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2557. Min Act: -0.1700
Data Index: 5862873 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 120752 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 6858591 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 7370936 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 8484605 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2557. Min Act: -0.1700
Data Index: 71001 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1932. Min Act: -0.1700
Data Index: 4930019 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1932. Min Act: -0.1700
Data Index: 456050 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19