Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5018. Min Range: -5.5018
Max Act: 5.5018. Min Act: -0.1700
Data Index: 5905509 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5018. Min Range: -5.5018
Max Act: 5.2518. Min Act: -0.1700
Data Index: 4807815 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5018. Min Range: -5.5018
Max Act: 5.0955. Min Act: -0.1700
Data Index: 2212018 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5018. Min Range: -5.5018
Max Act: 5.0330. Min Act: -0.1700
Data Index: 1607081 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5018. Min Range: -5.5018
Max Act: 5.0018. Min Act: -0.1700
Data Index: 5332854 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5018. Min Range: -5.5018
Max Act: 5.0330. Min Act: -0.1700
Data Index: 540742 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.9393. Min Act: -0.1700
Data Index: 2009633 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.8768. Min Act: -0.1700
Data Index: 7221591 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.8768. Min Act: -0.1700
Data Index: 507041 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.8143. Min Act: -0.1700
Data Index: 855313 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.8455. Min Act: -0.1700
Data Index: 4682991 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.8143. Min Act: -0.1700
Data Index: 1270544 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.8455. Min Act: -0.1700
Data Index: 8037114 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.8143. Min Act: -0.1700
Data Index: 6354211 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.7830. Min Act: -0.1700
Data Index: 2685079 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.7830. Min Act: -0.1700
Data Index: 5960054 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.7830. Min Act: -0.1700
Data Index: 1729334 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.7830. Min Act: -0.1700
Data Index: 7387207 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.7830. Min Act: -0.1700
Data Index: 2541341 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5018. Min Range: -5.5018
Max Act: 4.7830. Min Act: -0.1700
Data Index: 7956967 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19