Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 964 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.3641. Min Act: -0.1700
Data Index: 3409064 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2703. Min Act: -0.1700
Data Index: 1493126 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2391. Min Act: -0.1700
Data Index: 4994318 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2391. Min Act: -0.1700
Data Index: 7300019 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2391. Min Act: -0.1700
Data Index: 7225684 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2078. Min Act: -0.1700
Data Index: 8125845 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2391. Min Act: -0.1700
Data Index: 3717537 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2078. Min Act: -0.1700
Data Index: 3510967 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2078. Min Act: -0.1700
Data Index: 6407404 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2078. Min Act: -0.1700
Data Index: 6325673 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1766. Min Act: -0.1700
Data Index: 14537 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1766. Min Act: -0.1700
Data Index: 55217 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2078. Min Act: -0.1700
Data Index: 6664065 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.2078. Min Act: -0.1700
Data Index: 3306328 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1453. Min Act: -0.1700
Data Index: 8076174 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1453. Min Act: -0.1700
Data Index: 969205 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1453. Min Act: -0.1700
Data Index: 1186746 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1453. Min Act: -0.1700
Data Index: 5483142 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1453. Min Act: -0.1700
Data Index: 3741271 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3641. Min Range: -5.3641
Max Act: 5.1453. Min Act: -0.1700
Data Index: 4742827 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19