Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.3242. Min Act: -0.1700
Data Index: 6268714 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.3242. Min Act: -0.1700
Data Index: 7529565 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.2617. Min Act: -0.1700
Data Index: 8371171 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.1367. Min Act: -0.1700
Data Index: 3520978 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.1367. Min Act: -0.1700
Data Index: 2138792 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.1367. Min Act: -0.1700
Data Index: 8790890 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.0742. Min Act: -0.1700
Data Index: 8136619 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3919005 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.0117. Min Act: -0.1700
Data Index: 7929366 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3328698 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9804. Min Act: -0.1700
Data Index: 6855247 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.0117. Min Act: -0.1700
Data Index: 5910641 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3242. Min Range: -7.3242
Max Act: 7.0117. Min Act: -0.1700
Data Index: 8784918 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9804. Min Act: -0.1700
Data Index: 3033097 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9804. Min Act: -0.1699
Data Index: 4283878 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9492. Min Act: -0.1700
Data Index: 2027513 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9492. Min Act: -0.1700
Data Index: 7323528 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9492. Min Act: -0.1700
Data Index: 7319386 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9492. Min Act: -0.1700
Data Index: 6588034 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3242. Min Range: -7.3242
Max Act: 6.9804. Min Act: -0.1700
Data Index: 8759776 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19