Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1618. Min Range: -8.1618
Max Act: 8.1618. Min Act: -0.1700
Data Index: 1987798 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1618. Min Range: -8.1618
Max Act: 8.0680. Min Act: -0.1700
Data Index: 5470288 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1618. Min Range: -8.1618
Max Act: 8.0680. Min Act: -0.1700
Data Index: 8690995 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1618. Min Range: -8.1618
Max Act: 8.0680. Min Act: -0.1700
Data Index: 5470290 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.9743. Min Act: -0.1700
Data Index: 5446135 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.9743. Min Act: -0.1700
Data Index: 8690998 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.9430. Min Act: -0.1700
Data Index: 8484177 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.9430. Min Act: -0.1700
Data Index: 2047762 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.9118. Min Act: -0.1700
Data Index: 4256489 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.9118. Min Act: -0.1700
Data Index: 3565335 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.9118. Min Act: -0.1700
Data Index: 1143204 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.8493. Min Act: -0.1700
Data Index: 874978 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.8805. Min Act: -0.1700
Data Index: 6604100 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.8805. Min Act: -0.1700
Data Index: 1630328 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.8493. Min Act: -0.1700
Data Index: 3925826 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.8805. Min Act: -0.1700
Data Index: 7508238 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.8493. Min Act: -0.1700
Data Index: 4928891 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.8180. Min Act: -0.1700
Data Index: 3575067 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.7868. Min Act: -0.1700
Data Index: 2743749 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1618. Min Range: -8.1618
Max Act: 7.7868. Min Act: -0.1700
Data Index: 1701528 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19