Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.8087. Min Act: -0.1700
Data Index: 3020419 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.5587. Min Act: -0.1700
Data Index: 4534167 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.4962. Min Act: -0.1700
Data Index: 445027 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.4649. Min Act: -0.1700
Data Index: 2418771 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.4024. Min Act: -0.1700
Data Index: 1912308 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.3712. Min Act: -0.1700
Data Index: 2110134 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.3087. Min Act: -0.1700
Data Index: 696983 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.3087. Min Act: -0.1700
Data Index: 4837233 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2774. Min Act: -0.1700
Data Index: 3299149 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.3087. Min Act: -0.1700
Data Index: 2485984 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2774. Min Act: -0.1700
Data Index: 6236848 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2462. Min Act: -0.1700
Data Index: 8174001 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2462. Min Act: -0.1700
Data Index: 8494887 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2149. Min Act: -0.1700
Data Index: 7023772 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2149. Min Act: -0.1700
Data Index: 5253069 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.1837. Min Act: -0.1700
Data Index: 7753751 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2149. Min Act: -0.1700
Data Index: 3244379 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.1837. Min Act: -0.1700
Data Index: 272983 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.1837. Min Act: -0.1700
Data Index: 5369480 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8087. Min Range: -6.8087
Max Act: 6.2149. Min Act: -0.1700
Data Index: 1126749 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19