Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2486 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.5010. Min Act: -0.1700
Data Index: 5745124 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2815. Min Act: -0.1700
Data Index: 2694753 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2344. Min Act: -0.1700
Data Index: 978272 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2344. Min Act: -0.1700
Data Index: 6787919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2501. Min Act: -0.1700
Data Index: 5826117 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2344. Min Act: -0.1700
Data Index: 2848931 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2344. Min Act: -0.1700
Data Index: 6837961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2344. Min Act: -0.1700
Data Index: 1967322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2344. Min Act: -0.1700
Data Index: 80550 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1715. Min Act: -0.1700
Data Index: 3835518 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1400. Min Act: -0.1700
Data Index: 8685462 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1400. Min Act: -0.1700
Data Index: 535973 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1400. Min Act: -0.1700
Data Index: 3623774 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1242. Min Act: -0.1700
Data Index: 2169392 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1085. Min Act: -0.1700
Data Index: 5340667 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1400. Min Act: -0.1700
Data Index: 8535459 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1085. Min Act: -0.1700
Data Index: 5817660 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.1085. Min Act: -0.1700
Data Index: 3568921 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.0927. Min Act: -0.1700
Data Index: 7628185 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.0770. Min Act: -0.1700
Data Index: 3579737 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19