Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5305 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.8848. Min Act: -0.1700
Data Index: 4648812 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.7598. Min Act: -0.1700
Data Index: 6356947 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.6973. Min Act: -0.1700
Data Index: 3708787 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.5723. Min Act: -0.1700
Data Index: 6837472 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.5411. Min Act: -0.1700
Data Index: 5981613 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.5098. Min Act: -0.1700
Data Index: 4798418 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.4786. Min Act: -0.1700
Data Index: 8672414 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.4473. Min Act: -0.1700
Data Index: 7221132 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.4786. Min Act: -0.1700
Data Index: 905429 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.4473. Min Act: -0.1700
Data Index: 3210064 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.4161. Min Act: -0.1700
Data Index: 659374 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.3848. Min Act: -0.1700
Data Index: 3349865 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.3848. Min Act: -0.1700
Data Index: 4741566 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.3536. Min Act: -0.1700
Data Index: 8669660 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.3536. Min Act: -0.1700
Data Index: 6215242 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.3223. Min Act: -0.1700
Data Index: 545309 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.3223. Min Act: -0.1700
Data Index: 3633810 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.3223. Min Act: -0.1700
Data Index: 4800454 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.2911. Min Act: -0.1700
Data Index: 3274030 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8848. Min Range: -7.8848
Max Act: 7.2911. Min Act: -0.1700
Data Index: 1114946 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19