Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9782. Min Act: -0.1700
Data Index: 7070514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9470. Min Act: -0.1700
Data Index: 2817930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9782. Min Act: -0.1700
Data Index: 2612934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9782. Min Act: -0.1700
Data Index: 4224203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9782. Min Act: -0.1700
Data Index: 4199147 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9157. Min Act: -0.1700
Data Index: 1835129 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9470. Min Act: -0.1700
Data Index: 4635723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9157. Min Act: -0.1700
Data Index: 8370807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.8844. Min Act: -0.1700
Data Index: 8276632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9157. Min Act: -0.1700
Data Index: 6086438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9157. Min Act: -0.1700
Data Index: 617455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.8844. Min Act: -0.1700
Data Index: 7628796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9157. Min Act: -0.1700
Data Index: 1600649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.9157. Min Act: -0.1700
Data Index: 513157 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.8219. Min Act: -0.1700
Data Index: 1983940 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.7906. Min Act: -0.1700
Data Index: 2318644 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.7594. Min Act: -0.1700
Data Index: 2045903 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.7906. Min Act: -0.1700
Data Index: 8742021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.7906. Min Act: -0.1700
Data Index: 8024939 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9782. Min Range: -3.9782
Max Act: 3.7281. Min Act: -0.1700
Data Index: 7734606 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19