Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3714 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.8023. Min Act: -0.1700
Data Index: 3962065 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.2710. Min Act: -0.1700
Data Index: 8443116 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.2398. Min Act: -0.1700
Data Index: 5843983 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.2398. Min Act: -0.1700
Data Index: 4720150 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.1773. Min Act: -0.1700
Data Index: 1457997 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.1773. Min Act: -0.1700
Data Index: 4575641 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.1460. Min Act: -0.1700
Data Index: 2228323 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.1460. Min Act: -0.1700
Data Index: 3397919 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.1773. Min Act: -0.1700
Data Index: 348206 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.0835. Min Act: -0.1700
Data Index: 2940333 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.0523. Min Act: -0.1700
Data Index: 819888 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.0523. Min Act: -0.1700
Data Index: 1446027 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8023. Min Range: -6.8023
Max Act: 5.9585. Min Act: -0.1700
Data Index: 7600436 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8023. Min Range: -6.8023
Max Act: 6.0210. Min Act: -0.1700
Data Index: 517798 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8023. Min Range: -6.8023
Max Act: 5.9898. Min Act: -0.1700
Data Index: 7714569 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8023. Min Range: -6.8023
Max Act: 5.9898. Min Act: -0.1700
Data Index: 1301928 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8023. Min Range: -6.8023
Max Act: 5.9585. Min Act: -0.1700
Data Index: 5183366 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8023. Min Range: -6.8023
Max Act: 5.9585. Min Act: -0.1700
Data Index: 6258462 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8023. Min Range: -6.8023
Max Act: 5.8648. Min Act: -0.1700
Data Index: 6559868 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8023. Min Range: -6.8023
Max Act: 5.8960. Min Act: -0.1700
Data Index: 2793974 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19