Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3907 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.3886. Min Act: -0.1700
Data Index: 7005186 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.1386. Min Act: -0.1700
Data Index: 7479953 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.1074. Min Act: -0.1700
Data Index: 5055076 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.1074. Min Act: -0.1700
Data Index: 668197 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0761. Min Act: -0.1700
Data Index: 3419449 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.1074. Min Act: -0.1700
Data Index: 4622647 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0761. Min Act: -0.1700
Data Index: 2351268 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7883809 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0761. Min Act: -0.1700
Data Index: 5181234 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0761. Min Act: -0.1700
Data Index: 2127841 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0761. Min Act: -0.1700
Data Index: 7804430 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0449. Min Act: -0.1700
Data Index: 4974732 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3886. Min Range: -6.3886
Max Act: 5.9824. Min Act: -0.1700
Data Index: 1140526 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3488476 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3886. Min Range: -6.3886
Max Act: 5.9824. Min Act: -0.1700
Data Index: 2153409 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3886. Min Range: -6.3886
Max Act: 5.9824. Min Act: -0.1700
Data Index: 635017 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3886. Min Range: -6.3886
Max Act: 5.9824. Min Act: -0.1700
Data Index: 4486436 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3886. Min Range: -6.3886
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3484891 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3886. Min Range: -6.3886
Max Act: 5.9511. Min Act: -0.1700
Data Index: 6885315 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3886. Min Range: -6.3886
Max Act: 5.9511. Min Act: -0.1700
Data Index: 7245014 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19