Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2010 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.6886. Min Act: -0.1700
Data Index: 1608844 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.6886. Min Act: -0.1700
Data Index: 3214591 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3761. Min Act: -0.1700
Data Index: 5504147 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3449. Min Act: -0.1700
Data Index: 4421278 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3136. Min Act: -0.1700
Data Index: 2860117 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.2199. Min Act: -0.1700
Data Index: 3739304 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.1886. Min Act: -0.1700
Data Index: 6952451 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.2199. Min Act: -0.1700
Data Index: 4064200 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.1261. Min Act: -0.1700
Data Index: 774877 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0949. Min Act: -0.1700
Data Index: 471138 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0949. Min Act: -0.1700
Data Index: 2264205 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0636. Min Act: -0.1700
Data Index: 3726068 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0636. Min Act: -0.1700
Data Index: 6523544 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0636. Min Act: -0.1700
Data Index: 3913753 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0324. Min Act: -0.1700
Data Index: 2066022 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0324. Min Act: -0.1700
Data Index: 6902252 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0011. Min Act: -0.1700
Data Index: 8527619 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.0324. Min Act: -0.1700
Data Index: 2253097 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6886. Min Range: -6.6886
Max Act: 5.9699. Min Act: -0.1700
Data Index: 8454394 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6886. Min Range: -6.6886
Max Act: 5.9699. Min Act: -0.1700
Data Index: 3850362 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19