Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1817. Min Act: -0.1700
Data Index: 8316407 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1641. Min Act: -0.1700
Data Index: 6379123 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1466. Min Act: -0.1700
Data Index: 4117950 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1466. Min Act: -0.1700
Data Index: 4148831 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1466. Min Act: -0.1700
Data Index: 2428595 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1290. Min Act: -0.1700
Data Index: 1653214 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 5641266 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1290. Min Act: -0.1700
Data Index: 169221 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1290. Min Act: -0.1700
Data Index: 6203667 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 6230645 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 1348157 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.0939. Min Act: -0.1700
Data Index: 2392408 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 8068663 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 6288586 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1290. Min Act: -0.1700
Data Index: 2239768 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 728504 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 5921872 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 5560783 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.1115. Min Act: -0.1700
Data Index: 1654915 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1817. Min Range: -1.1817
Max Act: 1.0939. Min Act: -0.1700
Data Index: 4870093 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19