Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5343. Min Range: -7.5343
Max Act: 7.5343. Min Act: -0.1700
Data Index: 690545 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5343. Min Range: -7.5343
Max Act: 7.3468. Min Act: -0.1700
Data Index: 1317430 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5343. Min Range: -7.5343
Max Act: 7.0968. Min Act: -0.1700
Data Index: 3469384 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5343. Min Range: -7.5343
Max Act: 7.0655. Min Act: -0.1700
Data Index: 3972433 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.9093. Min Act: -0.1700
Data Index: 3141009 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.9093. Min Act: -0.1700
Data Index: 1479577 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.9093. Min Act: -0.1700
Data Index: 826002 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.9093. Min Act: -0.1700
Data Index: 2352149 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.8780. Min Act: -0.1700
Data Index: 7031550 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.7218. Min Act: -0.1700
Data Index: 7783670 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.8780. Min Act: -0.1700
Data Index: 2362445 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.8468. Min Act: -0.1700
Data Index: 5820501 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.8155. Min Act: -0.1700
Data Index: 5421056 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.7843. Min Act: -0.1700
Data Index: 3343784 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.7843. Min Act: -0.1700
Data Index: 2511867 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.7843. Min Act: -0.1700
Data Index: 2668993 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.6905. Min Act: -0.1700
Data Index: 1540067 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.6593. Min Act: -0.1700
Data Index: 7452292 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.6905. Min Act: -0.1700
Data Index: 334622 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5343. Min Range: -7.5343
Max Act: 6.6593. Min Act: -0.1700
Data Index: 4778819 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19