Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.2746. Min Act: -0.1700
Data Index: 8553675 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.2121. Min Act: -0.1700
Data Index: 5666885 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.2121. Min Act: -0.1700
Data Index: 1814219 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.2121. Min Act: -0.1700
Data Index: 6150418 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.1808. Min Act: -0.1700
Data Index: 3921759 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.1496. Min Act: -0.1700
Data Index: 7727811 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.1183. Min Act: -0.1700
Data Index: 695694 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.0558. Min Act: -0.1700
Data Index: 7735565 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2746. Min Range: -5.2746
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3886416 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9933. Min Act: -0.1700
Data Index: 4144187 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9933. Min Act: -0.1700
Data Index: 4544577 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9933. Min Act: -0.1700
Data Index: 6879986 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9933. Min Act: -0.1700
Data Index: 3856041 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9621. Min Act: -0.1700
Data Index: 5565855 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9621. Min Act: -0.1700
Data Index: 4235265 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9621. Min Act: -0.1700
Data Index: 5328437 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9621. Min Act: -0.1700
Data Index: 6537897 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9621. Min Act: -0.1700
Data Index: 2835117 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9621. Min Act: -0.1700
Data Index: 6116653 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2746. Min Range: -5.2746
Max Act: 4.9621. Min Act: -0.1700
Data Index: 6334743 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19