Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3341 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1415. Min Act: -0.1700
Data Index: 1102764 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1258. Min Act: -0.1700
Data Index: 7691140 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1573. Min Act: -0.1700
Data Index: 257834 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1100. Min Act: -0.1700
Data Index: 5678016 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1258. Min Act: -0.1700
Data Index: 4200542 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1100. Min Act: -0.1700
Data Index: 886218 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1100. Min Act: -0.1700
Data Index: 4459959 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1258. Min Act: -0.1700
Data Index: 149391 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1100. Min Act: -0.1700
Data Index: 1950730 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1100. Min Act: -0.1700
Data Index: 653969 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1415. Min Act: -0.1700
Data Index: 7572214 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.1100. Min Act: -0.1700
Data Index: 500073 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0785. Min Act: -0.1700
Data Index: 1359413 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0943. Min Act: -0.1700
Data Index: 5101704 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0627. Min Act: -0.1700
Data Index: 8068621 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0943. Min Act: -0.1700
Data Index: 1175511 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0785. Min Act: -0.1700
Data Index: 6867018 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0943. Min Act: -0.1700
Data Index: 2859773 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0785. Min Act: -0.1700
Data Index: 4944521 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1573. Min Range: -3.1573
Max Act: 3.0785. Min Act: -0.1700
Data Index: 5344594 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19