Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.6497. Min Act: -0.1700
Data Index: 1263677 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.3372. Min Act: -0.1700
Data Index: 4194920 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.3372. Min Act: -0.1700
Data Index: 848377 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.2747. Min Act: -0.1700
Data Index: 3739133 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.2434. Min Act: -0.1700
Data Index: 7547426 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.2434. Min Act: -0.1700
Data Index: 1109323 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.2434. Min Act: -0.1700
Data Index: 1109335 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.2122. Min Act: -0.1700
Data Index: 7141482 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.1809. Min Act: -0.1700
Data Index: 6209058 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.1809. Min Act: -0.1700
Data Index: 5215128 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.1497. Min Act: -0.1700
Data Index: 7937216 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.1497. Min Act: -0.1700
Data Index: 1927525 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.1497. Min Act: -0.1700
Data Index: 1555232 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.1497. Min Act: -0.1700
Data Index: 6777642 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.1184. Min Act: -0.1700
Data Index: 8008887 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.0872. Min Act: -0.1700
Data Index: 5116300 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.0872. Min Act: -0.1700
Data Index: 3353652 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.0872. Min Act: -0.1700
Data Index: 3153198 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.0872. Min Act: -0.1700
Data Index: 1349933 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6497. Min Range: -6.6497
Max Act: 6.0872. Min Act: -0.1700
Data Index: 604439 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19