Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1118 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.9114. Min Act: -0.1700
Data Index: 472757 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.7864. Min Act: -0.1700
Data Index: 4604646 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.7239. Min Act: -0.1700
Data Index: 4776613 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.7551. Min Act: -0.1700
Data Index: 5282847 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.7551. Min Act: -0.1700
Data Index: 7935126 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.7864. Min Act: -0.1700
Data Index: 4776630 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.7239. Min Act: -0.1700
Data Index: 4604649 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.7551. Min Act: -0.1700
Data Index: 345181 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.6301. Min Act: -0.1700
Data Index: 309624 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.6301. Min Act: -0.1700
Data Index: 4776615 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.5676. Min Act: -0.1700
Data Index: 8476078 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.5676. Min Act: -0.1700
Data Index: 2597300 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.5676. Min Act: -0.1700
Data Index: 58457 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.5364. Min Act: -0.1700
Data Index: 6939583 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.5364. Min Act: -0.1700
Data Index: 1566549 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.4426. Min Act: -0.1700
Data Index: 5800359 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.4426. Min Act: -0.1700
Data Index: 2929411 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.4114. Min Act: -0.1700
Data Index: 25491 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.4114. Min Act: -0.1700
Data Index: 3018292 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9114. Min Range: -5.9114
Max Act: 5.3801. Min Act: -0.1700
Data Index: 4745824 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19