Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5046 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.2535. Min Act: -0.1700
Data Index: 4394673 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.1910. Min Act: -0.1700
Data Index: 2507667 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.1910. Min Act: -0.1700
Data Index: 2112277 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.0660. Min Act: -0.1700
Data Index: 3506114 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.0660. Min Act: -0.1700
Data Index: 1969365 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.0660. Min Act: -0.1700
Data Index: 3935148 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.0660. Min Act: -0.1700
Data Index: 6771122 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.0660. Min Act: -0.1700
Data Index: 321571 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.0035. Min Act: -0.1700
Data Index: 6211155 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.9410. Min Act: -0.1700
Data Index: 4109139 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2535. Min Range: -10.2535
Max Act: 10.0035. Min Act: -0.1700
Data Index: 6333676 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.9410. Min Act: -0.1700
Data Index: 6997889 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.9410. Min Act: -0.1700
Data Index: 3420074 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.9410. Min Act: -0.1700
Data Index: 669803 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.8785. Min Act: -0.1700
Data Index: 4109141 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.8785. Min Act: -0.1700
Data Index: 5565071 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.8785. Min Act: -0.1700
Data Index: 5824368 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.8785. Min Act: -0.1700
Data Index: 4886371 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.7535. Min Act: -0.1700
Data Index: 4885617 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2535. Min Range: -10.2535
Max Act: 9.7535. Min Act: -0.1700
Data Index: 2727316 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19