Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3980 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.8442. Min Act: -0.1700
Data Index: 3894480 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.8283. Min Act: -0.1700
Data Index: 4094615 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.8124. Min Act: -0.1700
Data Index: 7513701 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.8283. Min Act: -0.1700
Data Index: 1980598 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7965. Min Act: -0.1700
Data Index: 1200098 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7806. Min Act: -0.1700
Data Index: 4005474 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7806. Min Act: -0.1700
Data Index: 7565136 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7806. Min Act: -0.1700
Data Index: 8176782 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7806. Min Act: -0.1700
Data Index: 4170895 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7806. Min Act: -0.1700
Data Index: 2570860 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7486. Min Act: -0.1700
Data Index: 8810775 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7486. Min Act: -0.1700
Data Index: 1856146 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7646. Min Act: -0.1700
Data Index: 5019885 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7486. Min Act: -0.1700
Data Index: 1103673 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7486. Min Act: -0.1700
Data Index: 2263318 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7486. Min Act: -0.1700
Data Index: 1447688 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7167. Min Act: -0.1700
Data Index: 8179140 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7327. Min Act: -0.1700
Data Index: 76006 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7167. Min Act: -0.1700
Data Index: 7824491 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8442. Min Range: -2.8442
Max Act: 2.7167. Min Act: -0.1700
Data Index: 8512003 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19