Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.7034. Min Act: -0.1700
Data Index: 7519939 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.6721. Min Act: -0.1700
Data Index: 8386845 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.6408. Min Act: -0.1700
Data Index: 744622 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.4843. Min Act: -0.1700
Data Index: 3122703 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.4686. Min Act: -0.1700
Data Index: 2715439 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.4373. Min Act: -0.1700
Data Index: 5180093 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.4373. Min Act: -0.1700
Data Index: 6488962 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3902. Min Act: -0.1700
Data Index: 4994921 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3746. Min Act: -0.1700
Data Index: 6735371 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3589. Min Act: -0.1700
Data Index: 1663880 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3589. Min Act: -0.1700
Data Index: 3357839 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3432. Min Act: -0.1700
Data Index: 7426243 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3432. Min Act: -0.1700
Data Index: 4934872 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3275. Min Act: -0.1700
Data Index: 2241014 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3118. Min Act: -0.1700
Data Index: 7465239 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3118. Min Act: -0.1700
Data Index: 486572 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.3275. Min Act: -0.1700
Data Index: 8589228 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.2961. Min Act: -0.1700
Data Index: 3354318 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.2961. Min Act: -0.1700
Data Index: 1872315 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7034. Min Range: -3.7034
Max Act: 3.2804. Min Act: -0.1700
Data Index: 6258933 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19