Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.1548. Min Act: -0.1700
Data Index: 8780666 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0610. Min Act: -0.1700
Data Index: 731237 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0610. Min Act: -0.1700
Data Index: 5749615 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0923. Min Act: -0.1700
Data Index: 2922321 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9672. Min Act: -0.1700
Data Index: 7075532 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9360. Min Act: -0.1700
Data Index: 5170024 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9203. Min Act: -0.1700
Data Index: 1675244 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9672. Min Act: -0.1700
Data Index: 7297846 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9203. Min Act: -0.1700
Data Index: 8698300 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9047. Min Act: -0.1700
Data Index: 85936 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.8265. Min Act: -0.1700
Data Index: 4370310 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.8109. Min Act: -0.1700
Data Index: 3313427 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.8265. Min Act: -0.1700
Data Index: 4774186 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.7952. Min Act: -0.1700
Data Index: 963469 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.7952. Min Act: -0.1700
Data Index: 1181665 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.7952. Min Act: -0.1700
Data Index: 6771722 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.8422. Min Act: -0.1700
Data Index: 5000567 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.8109. Min Act: -0.1700
Data Index: 1592726 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.8109. Min Act: -0.1700
Data Index: 282225 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.8109. Min Act: -0.1700
Data Index: 8708148 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19