Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1860 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.4342. Min Act: -0.1700
Data Index: 644989 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.4030. Min Act: -0.1700
Data Index: 8821808 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3717. Min Act: -0.1700
Data Index: 6463687 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3405. Min Act: -0.1700
Data Index: 3574844 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3717. Min Act: -0.1700
Data Index: 4132513 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3092. Min Act: -0.1700
Data Index: 1967235 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3405. Min Act: -0.1700
Data Index: 490089 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3092. Min Act: -0.1700
Data Index: 4478442 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2780. Min Act: -0.1700
Data Index: 8021861 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3092. Min Act: -0.1700
Data Index: 1451848 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2780. Min Act: -0.1700
Data Index: 8607336 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2467. Min Act: -0.1700
Data Index: 6233263 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2467. Min Act: -0.1700
Data Index: 6384287 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2467. Min Act: -0.1700
Data Index: 6562540 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2155. Min Act: -0.1700
Data Index: 3069993 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2155. Min Act: -0.1700
Data Index: 2004763 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2155. Min Act: -0.1700
Data Index: 4879950 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2155. Min Act: -0.1700
Data Index: 5119115 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2155. Min Act: -0.1700
Data Index: 6121129 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2155. Min Act: -0.1700
Data Index: 494735 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19