Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.6077. Min Act: -0.1700
Data Index: 4754059 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.6077. Min Act: -0.1700
Data Index: 3142249 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.2640. Min Act: -0.1700
Data Index: 7727476 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.1702. Min Act: -0.1700
Data Index: 428411 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.1077. Min Act: -0.1700
Data Index: 4027025 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.0765. Min Act: -0.1700
Data Index: 8803515 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.0452. Min Act: -0.1700
Data Index: 1319384 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.0452. Min Act: -0.1700
Data Index: 1592649 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9827. Min Act: -0.1700
Data Index: 4283083 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6077. Min Range: -6.6077
Max Act: 6.0140. Min Act: -0.1700
Data Index: 4027026 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9827. Min Act: -0.1700
Data Index: 4797096 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9827. Min Act: -0.1700
Data Index: 5338876 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9202. Min Act: -0.1700
Data Index: 7273918 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9202. Min Act: -0.1700
Data Index: 600136 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9202. Min Act: -0.1700
Data Index: 141806 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9202. Min Act: -0.1700
Data Index: 5713939 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9515. Min Act: -0.1700
Data Index: 4972893 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9202. Min Act: -0.1700
Data Index: 1425371 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.8577. Min Act: -0.1700
Data Index: 1096303 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6077. Min Range: -6.6077
Max Act: 5.9202. Min Act: -0.1700
Data Index: 3911438 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19