Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.6232. Min Act: -0.1700
Data Index: 7406664 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.5763. Min Act: -0.1700
Data Index: 3515796 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.4667. Min Act: -0.1700
Data Index: 1778217 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.4510. Min Act: -0.1700
Data Index: 1942799 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.4510. Min Act: -0.1700
Data Index: 5176308 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.3883. Min Act: -0.1700
Data Index: 6722014 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.3569. Min Act: -0.1700
Data Index: 2205049 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.3412. Min Act: -0.1700
Data Index: 7030010 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.3569. Min Act: -0.1700
Data Index: 2824402 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.3412. Min Act: -0.1700
Data Index: 7083593 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.3255. Min Act: -0.1700
Data Index: 6815005 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.3255. Min Act: -0.1700
Data Index: 1926486 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2941. Min Act: -0.1700
Data Index: 6332224 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2941. Min Act: -0.1700
Data Index: 6910481 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2941. Min Act: -0.1700
Data Index: 1119901 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2784. Min Act: -0.1700
Data Index: 4248618 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2627. Min Act: -0.1700
Data Index: 1026254 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2470. Min Act: -0.1700
Data Index: 5380829 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2627. Min Act: -0.1700
Data Index: 4779433 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6232. Min Range: -3.6232
Max Act: 3.2470. Min Act: -0.1700
Data Index: 706777 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19