Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2741 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0443. Min Range: -3.0443
Max Act: 3.0443. Min Act: -0.1700
Data Index: 6999710 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9969. Min Act: -0.1700
Data Index: 2993300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9969. Min Act: -0.1700
Data Index: 2843084 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9811. Min Act: -0.1700
Data Index: 8655313 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9811. Min Act: -0.1700
Data Index: 5624037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9811. Min Act: -0.1700
Data Index: 790466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9811. Min Act: -0.1700
Data Index: 197685 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9811. Min Act: -0.1700
Data Index: 5522225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9495. Min Act: -0.1700
Data Index: 8019597 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9495. Min Act: -0.1700
Data Index: 1997070 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9337. Min Act: -0.1700
Data Index: 3218215 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9178. Min Act: -0.1700
Data Index: 2320819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9178. Min Act: -0.1700
Data Index: 3960680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9178. Min Act: -0.1700
Data Index: 8622621 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9178. Min Act: -0.1700
Data Index: 4030914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9178. Min Act: -0.1700
Data Index: 3049919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9020. Min Act: -0.1700
Data Index: 1398181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9020. Min Act: -0.1700
Data Index: 3127776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9020. Min Act: -0.1700
Data Index: 6034508 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0443. Min Range: -3.0443
Max Act: 2.9178. Min Act: -0.1700
Data Index: 5358632 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19