Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4660 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.7101. Min Act: -0.1700
Data Index: 4220425 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.6788. Min Act: -0.1700
Data Index: 1044212 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.3656. Min Act: -0.1700
Data Index: 7683850 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.3186. Min Act: -0.1700
Data Index: 551011 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2715. Min Act: -0.1700
Data Index: 1917952 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2715. Min Act: -0.1700
Data Index: 4936832 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2715. Min Act: -0.1700
Data Index: 3852633 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2715. Min Act: -0.1700
Data Index: 4558711 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2557. Min Act: -0.1700
Data Index: 8307873 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2557. Min Act: -0.1700
Data Index: 6749476 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2557. Min Act: -0.1700
Data Index: 3950358 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2086. Min Act: -0.1700
Data Index: 2143127 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.2086. Min Act: -0.1700
Data Index: 8831154 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.1929. Min Act: -0.1700
Data Index: 5882480 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.1929. Min Act: -0.1700
Data Index: 5182917 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.1929. Min Act: -0.1700
Data Index: 1787490 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.1929. Min Act: -0.1700
Data Index: 7474986 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.1929. Min Act: -0.1700
Data Index: 670368 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.1614. Min Act: -0.1700
Data Index: 6414833 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7101. Min Range: -3.7101
Max Act: 3.1614. Min Act: -0.1700
Data Index: 6230747 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19