Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5376 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3791. Min Range: -6.3791
Max Act: 6.3791. Min Act: -0.1700
Data Index: 2602710 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3791. Min Range: -6.3791
Max Act: 6.1291. Min Act: -0.1700
Data Index: 5571237 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3791. Min Range: -6.3791
Max Act: 6.1291. Min Act: -0.1700
Data Index: 1651651 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3791. Min Range: -6.3791
Max Act: 6.0354. Min Act: -0.1700
Data Index: 5332960 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.9729. Min Act: -0.1700
Data Index: 8070663 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3791. Min Range: -6.3791
Max Act: 6.0041. Min Act: -0.1700
Data Index: 2896277 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.9104. Min Act: -0.1700
Data Index: 2608551 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.9104. Min Act: -0.1700
Data Index: 3722776 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.8166. Min Act: -0.1700
Data Index: 2719874 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.8166. Min Act: -0.1700
Data Index: 4089456 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.7541. Min Act: -0.1700
Data Index: 5709564 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.7541. Min Act: -0.1700
Data Index: 4878441 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6604. Min Act: -0.1700
Data Index: 282334 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6916. Min Act: -0.1700
Data Index: 781620 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6916. Min Act: -0.1700
Data Index: 5666972 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6916. Min Act: -0.1700
Data Index: 6874067 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6291. Min Act: -0.1700
Data Index: 8059624 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6604. Min Act: -0.1700
Data Index: 3026677 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6604. Min Act: -0.1700
Data Index: 1958068 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3791. Min Range: -6.3791
Max Act: 5.6916. Min Act: -0.1700
Data Index: 8457424 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19