Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2182 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9439. Min Act: -0.1700
Data Index: 5895829 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9609. Min Act: -0.1700
Data Index: 2339967 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9439. Min Act: -0.1700
Data Index: 5807749 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9439. Min Act: -0.1700
Data Index: 61289 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9269. Min Act: -0.1700
Data Index: 657997 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9099. Min Act: -0.1700
Data Index: 7505765 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8928. Min Act: -0.1697
Data Index: 1306782 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8928. Min Act: -0.1700
Data Index: 328004 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8928. Min Act: -0.1700
Data Index: 5595154 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8757. Min Act: -0.1700
Data Index: 2528872 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8928. Min Act: -0.1700
Data Index: 2234597 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8757. Min Act: -0.1700
Data Index: 5468942 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8757. Min Act: -0.1700
Data Index: 8466826 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8757. Min Act: -0.1700
Data Index: 7552648 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8757. Min Act: -0.1700
Data Index: 2799242 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8757. Min Act: -0.1700
Data Index: 5054257 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8757. Min Act: -0.1700
Data Index: 1705498 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8586. Min Act: -0.1700
Data Index: 461322 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8586. Min Act: -0.1700
Data Index: 5612553 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8586. Min Act: -0.1700
Data Index: 1141086 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19