Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2750 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.8376. Min Act: -0.1700
Data Index: 3699980 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.8063. Min Act: -0.1700
Data Index: 3718163 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.7438. Min Act: -0.1700
Data Index: 2304533 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.7438. Min Act: -0.1700
Data Index: 1552629 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.6501. Min Act: -0.1700
Data Index: 8217370 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.6188. Min Act: -0.1700
Data Index: 4720463 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.6501. Min Act: -0.1700
Data Index: 2647602 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.5876. Min Act: -0.1700
Data Index: 7574780 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.5563. Min Act: -0.1700
Data Index: 5130311 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.5563. Min Act: -0.1700
Data Index: 7079787 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4938. Min Act: -0.1700
Data Index: 5067301 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.5251. Min Act: -0.1700
Data Index: 8029359 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.5251. Min Act: -0.1700
Data Index: 5822098 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4626. Min Act: -0.1700
Data Index: 2541306 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4313. Min Act: -0.1700
Data Index: 8088812 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4313. Min Act: -0.1700
Data Index: 2972578 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4313. Min Act: -0.1700
Data Index: 5290235 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4313. Min Act: -0.1700
Data Index: 4425924 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4001. Min Act: -0.1700
Data Index: 7187140 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8376. Min Range: -5.8376
Max Act: 5.4001. Min Act: -0.1700
Data Index: 6415960 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19