Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.5848. Min Act: -0.1700
Data Index: 2117894 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.3973. Min Act: -0.1700
Data Index: 1471636 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.3973. Min Act: -0.1700
Data Index: 7385487 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.3348. Min Act: -0.1700
Data Index: 346788 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.3036. Min Act: -0.1700
Data Index: 555291 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.2723. Min Act: -0.1700
Data Index: 4895686 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.2411. Min Act: -0.1700
Data Index: 7031766 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.2098. Min Act: -0.1700
Data Index: 5057582 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.2411. Min Act: -0.1700
Data Index: 1334487 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.2098. Min Act: -0.1700
Data Index: 4485471 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.2098. Min Act: -0.1700
Data Index: 2074178 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1786. Min Act: -0.1700
Data Index: 1428411 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1786. Min Act: -0.1700
Data Index: 6294311 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1786. Min Act: -0.1700
Data Index: 322766 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1161. Min Act: -0.1700
Data Index: 4712835 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1786. Min Act: -0.1700
Data Index: 7119873 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1473. Min Act: -0.1700
Data Index: 1100488 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1473. Min Act: -0.1700
Data Index: 792439 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1161. Min Act: -0.1700
Data Index: 1000596 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5848. Min Range: -5.5848
Max Act: 5.1473. Min Act: -0.1700
Data Index: 1403969 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19