Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2954. Min Range: -7.2954
Max Act: 7.2954. Min Act: -0.1700
Data Index: 6297099 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2954. Min Range: -7.2954
Max Act: 7.2329. Min Act: -0.1700
Data Index: 3124901 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2954. Min Range: -7.2954
Max Act: 7.1079. Min Act: -0.1700
Data Index: 6298307 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2954. Min Range: -7.2954
Max Act: 7.0767. Min Act: -0.1700
Data Index: 2882209 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2954. Min Range: -7.2954
Max Act: 7.0142. Min Act: -0.1700
Data Index: 1676888 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.9829. Min Act: -0.1700
Data Index: 8672577 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.9517. Min Act: -0.1700
Data Index: 1148779 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.9517. Min Act: -0.1700
Data Index: 7594221 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.9204. Min Act: -0.1700
Data Index: 349149 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.8892. Min Act: -0.1700
Data Index: 4216804 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.8892. Min Act: -0.1700
Data Index: 337921 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.8579. Min Act: -0.1700
Data Index: 5361231 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.8892. Min Act: -0.1700
Data Index: 8618723 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.8579. Min Act: -0.1700
Data Index: 3633735 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.8579. Min Act: -0.1700
Data Index: 351829 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.8579. Min Act: -0.1700
Data Index: 6268855 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.7954. Min Act: -0.1700
Data Index: 7749716 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.7954. Min Act: -0.1700
Data Index: 7555560 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.7954. Min Act: -0.1700
Data Index: 8446867 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2954. Min Range: -7.2954
Max Act: 6.7642. Min Act: -0.1700
Data Index: 747880 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19