Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5561 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.7240. Min Act: -0.1700
Data Index: 3025401 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.6301. Min Act: -0.1700
Data Index: 301453 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.6614. Min Act: -0.1700
Data Index: 1591897 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5988. Min Act: -0.1700
Data Index: 970466 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5675. Min Act: -0.1700
Data Index: 5563938 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5675. Min Act: -0.1700
Data Index: 6500170 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5675. Min Act: -0.1700
Data Index: 6304440 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5675. Min Act: -0.1700
Data Index: 6250885 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5675. Min Act: -0.1700
Data Index: 4289046 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5362. Min Act: -0.1700
Data Index: 3178729 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5049. Min Act: -0.1700
Data Index: 3954516 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5049. Min Act: -0.1700
Data Index: 5502115 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5049. Min Act: -0.1700
Data Index: 771961 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.5049. Min Act: -0.1700
Data Index: 759915 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.4892. Min Act: -0.1700
Data Index: 771962 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.4892. Min Act: -0.1700
Data Index: 4960748 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.4892. Min Act: -0.1700
Data Index: 4151527 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.4892. Min Act: -0.1700
Data Index: 94592 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.4735. Min Act: -0.1700
Data Index: 7918274 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7240. Min Range: -3.7240
Max Act: 3.4735. Min Act: -0.1700
Data Index: 3918476 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19