Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.3137. Min Act: -0.1700
Data Index: 1824513 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.3137. Min Act: -0.1700
Data Index: 3495067 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.3137. Min Act: -0.1700
Data Index: 4944919 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.2512. Min Act: -0.1700
Data Index: 6792722 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.2199. Min Act: -0.1700
Data Index: 2989366 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1887. Min Act: -0.1700
Data Index: 4845332 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1574. Min Act: -0.1700
Data Index: 6897335 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1574. Min Act: -0.1700
Data Index: 5528830 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 4916610 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 5959874 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1574. Min Act: -0.1700
Data Index: 8755368 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1574. Min Act: -0.1700
Data Index: 8427476 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 1783447 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 272682 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 3840956 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 6412174 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 4335584 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 3540391 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0949. Min Act: -0.1700
Data Index: 6771233 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0949. Min Act: -0.1700
Data Index: 1473123 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19