Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1560 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9823. Min Act: -0.1700
Data Index: 7954860 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9823. Min Act: -0.1700
Data Index: 5549984 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9511. Min Act: -0.1700
Data Index: 233030 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9511. Min Act: -0.1700
Data Index: 1469285 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 2727699 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 3140680 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 4318533 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 4547232 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8573. Min Act: -0.1700
Data Index: 5254788 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 7195546 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 6761797 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8573. Min Act: -0.1700
Data Index: 6443741 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 8587910 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 2800701 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 8571283 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 6245420 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 369835 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8573. Min Act: -0.1700
Data Index: 3877735 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8573. Min Act: -0.1700
Data Index: 4673680 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8573. Min Act: -0.1700
Data Index: 580156 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19