Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1094 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0432. Min Range: -6.0432
Max Act: 6.0432. Min Act: -0.1700
Data Index: 2989647 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.6682. Min Act: -0.1700
Data Index: 1281480 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.6057. Min Act: -0.1700
Data Index: 5616104 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.5744. Min Act: -0.1700
Data Index: 866943 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.5744. Min Act: -0.1700
Data Index: 1663856 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.5119. Min Act: -0.1700
Data Index: 7282587 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4807. Min Act: -0.1700
Data Index: 5324142 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.5119. Min Act: -0.1700
Data Index: 8483184 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4807. Min Act: -0.1700
Data Index: 222528 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.5119. Min Act: -0.1700
Data Index: 4594173 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4807. Min Act: -0.1700
Data Index: 2475201 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4807. Min Act: -0.1700
Data Index: 489198 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4182. Min Act: -0.1700
Data Index: 3785796 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4807. Min Act: -0.1700
Data Index: 871902 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4494. Min Act: -0.1700
Data Index: 8469646 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4494. Min Act: -0.1700
Data Index: 3926201 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4182. Min Act: -0.1700
Data Index: 3556395 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4807. Min Act: -0.1700
Data Index: 8133142 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4494. Min Act: -0.1700
Data Index: 5833769 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.4494. Min Act: -0.1700
Data Index: 4172621 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19