Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1168. Min Range: -8.1168
Max Act: 8.1168. Min Act: -0.1700
Data Index: 8415383 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.7418. Min Act: -0.1700
Data Index: 148619 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.6480. Min Act: -0.1700
Data Index: 3509024 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.3355. Min Act: -0.1700
Data Index: 3222665 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.3043. Min Act: -0.1700
Data Index: 1261959 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.2730. Min Act: -0.1700
Data Index: 6710027 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.2730. Min Act: -0.1700
Data Index: 4852474 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.1793. Min Act: -0.1700
Data Index: 178178 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.1793. Min Act: -0.1700
Data Index: 5860698 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.1480. Min Act: -0.1700
Data Index: 4139983 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.1168. Min Act: -0.1700
Data Index: 6464378 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.1168. Min Act: -0.1700
Data Index: 7776922 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.0230. Min Act: -0.1700
Data Index: 3142517 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1168. Min Range: -8.1168
Max Act: 7.0543. Min Act: -0.1700
Data Index: 1489129 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1168. Min Range: -8.1168
Max Act: 6.9918. Min Act: -0.1700
Data Index: 3142510 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1168. Min Range: -8.1168
Max Act: 6.9605. Min Act: -0.1700
Data Index: 7118338 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1168. Min Range: -8.1168
Max Act: 6.9605. Min Act: -0.1700
Data Index: 2667429 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1168. Min Range: -8.1168
Max Act: 6.9605. Min Act: -0.1700
Data Index: 6530737 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1168. Min Range: -8.1168
Max Act: 6.9605. Min Act: -0.1700
Data Index: 1591345 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1168. Min Range: -8.1168
Max Act: 6.9293. Min Act: -0.1700
Data Index: 1565472 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19