Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.9640. Min Act: -0.1700
Data Index: 8415280 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7765. Min Act: -0.1700
Data Index: 7056787 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7765. Min Act: -0.1700
Data Index: 6973031 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7765. Min Act: -0.1700
Data Index: 7749837 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7453. Min Act: -0.1700
Data Index: 2713046 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7453. Min Act: -0.1700
Data Index: 4638871 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7140. Min Act: -0.1700
Data Index: 1708784 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7453. Min Act: -0.1700
Data Index: 3254863 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7453. Min Act: -0.1700
Data Index: 1220691 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.7140. Min Act: -0.1700
Data Index: 1563871 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6828. Min Act: -0.1700
Data Index: 1650316 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6828. Min Act: -0.1700
Data Index: 3003273 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6828. Min Act: -0.1700
Data Index: 7888762 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6515. Min Act: -0.1700
Data Index: 7225312 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6828. Min Act: -0.1700
Data Index: 5994890 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6828. Min Act: -0.1700
Data Index: 3694046 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6515. Min Act: -0.1700
Data Index: 3072813 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6515. Min Act: -0.1700
Data Index: 7738140 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6515. Min Act: -0.1700
Data Index: 6287838 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9640. Min Range: -5.9640
Max Act: 5.6828. Min Act: -0.1700
Data Index: 4362485 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19