Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.7212. Min Act: -0.1700
Data Index: 322524 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.6900. Min Act: -0.1700
Data Index: 2250931 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.6900. Min Act: -0.1700
Data Index: 6150107 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.6900. Min Act: -0.1700
Data Index: 8249231 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.6587. Min Act: -0.1700
Data Index: 1673134 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.6275. Min Act: -0.1700
Data Index: 1607915 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5962. Min Act: -0.1700
Data Index: 2470993 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5650. Min Act: -0.1700
Data Index: 7728517 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5337. Min Act: -0.1700
Data Index: 6323048 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5337. Min Act: -0.1700
Data Index: 2797058 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5337. Min Act: -0.1700
Data Index: 6708875 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5337. Min Act: -0.1700
Data Index: 4022957 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4712. Min Act: -0.1700
Data Index: 4178973 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4712. Min Act: -0.1700
Data Index: 2390416 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4712. Min Act: -0.1700
Data Index: 2888062 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4400. Min Act: -0.1700
Data Index: 4178962 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4400. Min Act: -0.1700
Data Index: 7572364 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4400. Min Act: -0.1700
Data Index: 7327785 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4400. Min Act: -0.1700
Data Index: 4178964 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4400. Min Act: -0.1700
Data Index: 7109935 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19