Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.9034. Min Act: -0.1700
Data Index: 1692236 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.7159. Min Act: -0.1700
Data Index: 1588751 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6846. Min Act: -0.1700
Data Index: 750160 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6221. Min Act: -0.1700
Data Index: 2681222 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6221. Min Act: -0.1700
Data Index: 237259 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6221. Min Act: -0.1700
Data Index: 5720777 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6221. Min Act: -0.1700
Data Index: 8412683 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5909. Min Act: -0.1700
Data Index: 1793695 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5596. Min Act: -0.1700
Data Index: 3365190 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5596. Min Act: -0.1700
Data Index: 5614748 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5596. Min Act: -0.1700
Data Index: 2744275 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5284. Min Act: -0.1700
Data Index: 6387591 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5284. Min Act: -0.1700
Data Index: 2684076 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5284. Min Act: -0.1700
Data Index: 1690998 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5284. Min Act: -0.1700
Data Index: 376080 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5284. Min Act: -0.1700
Data Index: 8383031 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5284. Min Act: -0.1700
Data Index: 4698237 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.4659. Min Act: -0.1700
Data Index: 7870377 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.4346. Min Act: -0.1700
Data Index: 3681980 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.4346. Min Act: -0.1700
Data Index: 2094362 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19