Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.1595. Min Act: -0.1700
Data Index: 5121846 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.0970. Min Act: -0.1700
Data Index: 4690784 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.0657. Min Act: -0.1700
Data Index: 6751977 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.0657. Min Act: -0.1700
Data Index: 6982112 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.0032. Min Act: -0.1700
Data Index: 1614325 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.0032. Min Act: -0.1700
Data Index: 1437338 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.0032. Min Act: -0.1700
Data Index: 8327967 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1595. Min Range: -5.1595
Max Act: 5.0032. Min Act: -0.1700
Data Index: 6305837 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9720. Min Act: -0.1700
Data Index: 4221782 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9720. Min Act: -0.1700
Data Index: 4151210 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9720. Min Act: -0.1700
Data Index: 7612662 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9720. Min Act: -0.1700
Data Index: 119783 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9407. Min Act: -0.1700
Data Index: 3990858 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9720. Min Act: -0.1700
Data Index: 6115412 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9095. Min Act: -0.1700
Data Index: 6957072 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9407. Min Act: -0.1700
Data Index: 8275135 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.8782. Min Act: -0.1700
Data Index: 7415414 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9095. Min Act: -0.1700
Data Index: 7053081 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9095. Min Act: -0.1700
Data Index: 6197865 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1595. Min Range: -5.1595
Max Act: 4.9095. Min Act: -0.1700
Data Index: 3799190 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19