Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3018 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1524. Min Range: -7.1524
Max Act: 7.1524. Min Act: -0.1700
Data Index: 7744394 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1524. Min Range: -7.1524
Max Act: 7.1524. Min Act: -0.1700
Data Index: 3228635 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1524. Min Range: -7.1524
Max Act: 7.0899. Min Act: -0.1700
Data Index: 41960 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.9649. Min Act: -0.1700
Data Index: 7395639 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.9024. Min Act: -0.1700
Data Index: 8530822 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.8086. Min Act: -0.1700
Data Index: 848708 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7774. Min Act: -0.1700
Data Index: 3886615 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7461. Min Act: -0.1700
Data Index: 1765636 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7149. Min Act: -0.1700
Data Index: 3927015 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7461. Min Act: -0.1700
Data Index: 4276423 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7149. Min Act: -0.1700
Data Index: 3455048 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7149. Min Act: -0.1700
Data Index: 5791864 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6524. Min Act: -0.1700
Data Index: 8327251 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6836. Min Act: -0.1700
Data Index: 6255537 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6524. Min Act: -0.1700
Data Index: 1141195 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7149. Min Act: -0.1700
Data Index: 8681177 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6211. Min Act: -0.1700
Data Index: 6176756 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6211. Min Act: -0.1700
Data Index: 3441099 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6524. Min Act: -0.1700
Data Index: 1236996 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6524. Min Act: -0.1700
Data Index: 1635692 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19