Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.3285. Min Act: -0.1700
Data Index: 8507947 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.3128. Min Act: -0.1700
Data Index: 4094700 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2971. Min Act: -0.1700
Data Index: 6139890 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.3128. Min Act: -0.1700
Data Index: 6045809 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2971. Min Act: -0.1700
Data Index: 8780197 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2657. Min Act: -0.1700
Data Index: 5769005 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2657. Min Act: -0.1700
Data Index: 3498647 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2186. Min Act: -0.1700
Data Index: 3992186 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2500. Min Act: -0.1700
Data Index: 3631217 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2186. Min Act: -0.1700
Data Index: 8499642 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2343. Min Act: -0.1700
Data Index: 6429914 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2028. Min Act: -0.1700
Data Index: 4871392 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2028. Min Act: -0.1700
Data Index: 3130972 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2028. Min Act: -0.1700
Data Index: 335013 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.2028. Min Act: -0.1700
Data Index: 3498648 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.1871. Min Act: -0.1700
Data Index: 2144624 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.1871. Min Act: -0.1700
Data Index: 405711 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.1871. Min Act: -0.1700
Data Index: 482877 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.1714. Min Act: -0.1700
Data Index: 482871 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3285. Min Range: -3.3285
Max Act: 3.1714. Min Act: -0.1700
Data Index: 1965342 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19