Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6336 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.3927. Min Act: -0.1700
Data Index: 4233496 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.3614. Min Act: -0.1700
Data Index: 1019478 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.3302. Min Act: -0.1700
Data Index: 3289715 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.3614. Min Act: -0.1700
Data Index: 7527987 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2989. Min Act: -0.1700
Data Index: 3446319 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2677. Min Act: -0.1700
Data Index: 232667 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2677. Min Act: -0.1700
Data Index: 3279687 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2677. Min Act: -0.1700
Data Index: 8023908 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2989. Min Act: -0.1700
Data Index: 7844270 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2677. Min Act: -0.1700
Data Index: 3405532 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2677. Min Act: -0.1700
Data Index: 1174173 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2364. Min Act: -0.1700
Data Index: 4513659 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2364. Min Act: -0.1700
Data Index: 7711738 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2364. Min Act: -0.1700
Data Index: 3285410 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2052. Min Act: -0.1700
Data Index: 7979724 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2052. Min Act: -0.1700
Data Index: 2115839 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2364. Min Act: -0.1700
Data Index: 1226812 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2052. Min Act: -0.1700
Data Index: 6734047 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2052. Min Act: -0.1700
Data Index: 7411662 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3927. Min Range: -5.3927
Max Act: 5.2052. Min Act: -0.1700
Data Index: 785588 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19