Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.2136. Min Act: -0.1700
Data Index: 6043871 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.0886. Min Act: -0.1700
Data Index: 6525453 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.0886. Min Act: -0.1700
Data Index: 1384280 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.0261. Min Act: -0.1700
Data Index: 7721455 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.0261. Min Act: -0.1700
Data Index: 5942587 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9949. Min Act: -0.1700
Data Index: 5942581 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.0261. Min Act: -0.1700
Data Index: 5768284 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.0261. Min Act: -0.1700
Data Index: 5589889 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2136. Min Range: -6.2136
Max Act: 6.0261. Min Act: -0.1700
Data Index: 5506449 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9949. Min Act: -0.1700
Data Index: 3513853 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9949. Min Act: -0.1700
Data Index: 1196709 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9949. Min Act: -0.1700
Data Index: 8684416 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9949. Min Act: -0.1700
Data Index: 8516504 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9949. Min Act: -0.1700
Data Index: 7946149 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9949. Min Act: -0.1700
Data Index: 657883 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9636. Min Act: -0.1700
Data Index: 7592977 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9636. Min Act: -0.1700
Data Index: 7170058 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9636. Min Act: -0.1700
Data Index: 7830768 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9636. Min Act: -0.1700
Data Index: 4333852 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2136. Min Range: -6.2136
Max Act: 5.9636. Min Act: -0.1700
Data Index: 2051169 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19