Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 114 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1841. Min Range: -8.1841
Max Act: 8.1841. Min Act: -0.1700
Data Index: 13221 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.4966. Min Act: -0.1700
Data Index: 2616902 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.4028. Min Act: -0.1700
Data Index: 6984365 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.3716. Min Act: -0.1700
Data Index: 7765593 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.3403. Min Act: -0.1700
Data Index: 3486386 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.2778. Min Act: -0.1700
Data Index: 4003514 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.2778. Min Act: -0.1700
Data Index: 4574261 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.2778. Min Act: -0.1700
Data Index: 7067885 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.2466. Min Act: -0.1700
Data Index: 4451183 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.2466. Min Act: -0.1700
Data Index: 7384241 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.1528. Min Act: -0.1700
Data Index: 8520806 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.1216. Min Act: -0.1700
Data Index: 3939782 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.0903. Min Act: -0.1700
Data Index: 2235077 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.0903. Min Act: -0.1700
Data Index: 3798781 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1841. Min Range: -8.1841
Max Act: 7.0591. Min Act: -0.1700
Data Index: 593461 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1841. Min Range: -8.1841
Max Act: 6.9653. Min Act: -0.1700
Data Index: 5832813 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1841. Min Range: -8.1841
Max Act: 6.9653. Min Act: -0.1700
Data Index: 5873294 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1841. Min Range: -8.1841
Max Act: 6.9341. Min Act: -0.1700
Data Index: 1838981 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1841. Min Range: -8.1841
Max Act: 6.9653. Min Act: -0.1700
Data Index: 114473 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1841. Min Range: -8.1841
Max Act: 6.9341. Min Act: -0.1700
Data Index: 989798 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19