Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 454 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.1615. Min Act: -0.1700
Data Index: 5394556 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.1615. Min Act: -0.1700
Data Index: 4642975 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.1615. Min Act: -0.1700
Data Index: 5557479 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6257660 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.1302. Min Act: -0.1700
Data Index: 1449706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.1302. Min Act: -0.1700
Data Index: 6626447 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0677. Min Act: -0.1700
Data Index: 7706085 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0990. Min Act: -0.1700
Data Index: 7474614 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0677. Min Act: -0.1700
Data Index: 4834379 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0677. Min Act: -0.1700
Data Index: 4612053 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0677. Min Act: -0.1700
Data Index: 7417160 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6281618 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0365. Min Act: -0.1700
Data Index: 4437943 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0365. Min Act: -0.1700
Data Index: 2695920 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0677. Min Act: -0.1700
Data Index: 3581714 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0052. Min Act: -0.1700
Data Index: 1441748 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0365. Min Act: -0.1700
Data Index: 5074901 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0365. Min Act: -0.1700
Data Index: 5017389 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0365. Min Act: -0.1700
Data Index: 7919814 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1615. Min Range: -5.1615
Max Act: 5.0365. Min Act: -0.1700
Data Index: 4876048 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19