Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 475 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1029. Min Range: -5.1029
Max Act: 5.1029. Min Act: -0.1700
Data Index: 4338429 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1029. Min Range: -5.1029
Max Act: 5.0404. Min Act: -0.1700
Data Index: 8152025 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1029. Min Range: -5.1029
Max Act: 5.0091. Min Act: -0.1700
Data Index: 6379480 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9154. Min Act: -0.1700
Data Index: 3039720 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9466. Min Act: -0.1700
Data Index: 1705887 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9466. Min Act: -0.1700
Data Index: 8749225 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9154. Min Act: -0.1700
Data Index: 3222219 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9154. Min Act: -0.1700
Data Index: 2795951 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9466. Min Act: -0.1700
Data Index: 6528888 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9466. Min Act: -0.1700
Data Index: 8117030 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9466. Min Act: -0.1700
Data Index: 8041714 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9154. Min Act: -0.1700
Data Index: 4375366 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.8841. Min Act: -0.1700
Data Index: 4615662 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.8841. Min Act: -0.1700
Data Index: 6760272 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.9154. Min Act: -0.1700
Data Index: 3857956 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.8841. Min Act: -0.1700
Data Index: 5447442 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.8841. Min Act: -0.1700
Data Index: 2889371 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.8841. Min Act: -0.1700
Data Index: 1415761 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.8841. Min Act: -0.1700
Data Index: 6846839 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1029. Min Range: -5.1029
Max Act: 4.8841. Min Act: -0.1700
Data Index: 6838229 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19