Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.7823. Min Act: -0.1700
Data Index: 6730588 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.6573. Min Act: -0.1700
Data Index: 7536985 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.5010. Min Act: -0.1700
Data Index: 3560214 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.3760. Min Act: -0.1700
Data Index: 5300758 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.3448. Min Act: -0.1700
Data Index: 221065 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.3135. Min Act: -0.1700
Data Index: 2086157 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.2510. Min Act: -0.1700
Data Index: 6303164 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.2510. Min Act: -0.1700
Data Index: 5687165 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.2198. Min Act: -0.1700
Data Index: 2160680 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.1573. Min Act: -0.1700
Data Index: 5440943 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.1885. Min Act: -0.1700
Data Index: 3658552 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.1885. Min Act: -0.1700
Data Index: 5848181 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.1260. Min Act: -0.1700
Data Index: 6869231 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.0948. Min Act: -0.1700
Data Index: 2859567 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.1260. Min Act: -0.1700
Data Index: 1927994 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.0635. Min Act: -0.1700
Data Index: 2756950 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.0323. Min Act: -0.1700
Data Index: 1358695 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.0948. Min Act: -0.1700
Data Index: 4509673 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.0635. Min Act: -0.1700
Data Index: 8784989 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.0635. Min Act: -0.1700
Data Index: 6063330 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19