Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.4337. Min Act: -0.1700
Data Index: 797012 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.3712. Min Act: -0.1700
Data Index: 8536499 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.3399. Min Act: -0.1700
Data Index: 143280 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.3087. Min Act: -0.1700
Data Index: 6542209 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.2774. Min Act: -0.1700
Data Index: 1000265 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.2149. Min Act: -0.1700
Data Index: 5104723 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.2149. Min Act: -0.1700
Data Index: 7007389 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.1837. Min Act: -0.1700
Data Index: 5661166 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.1837. Min Act: -0.1700
Data Index: 4763159 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.1524. Min Act: -0.1700
Data Index: 7805044 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.1524. Min Act: -0.1700
Data Index: 5396167 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.1212. Min Act: -0.1700
Data Index: 4779642 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.1212. Min Act: -0.1700
Data Index: 8188606 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.0899. Min Act: -0.1700
Data Index: 7190851 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.0587. Min Act: -0.1700
Data Index: 5761103 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.0587. Min Act: -0.1700
Data Index: 902071 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.0587. Min Act: -0.1700
Data Index: 6353143 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.0587. Min Act: -0.1700
Data Index: 986676 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.0587. Min Act: -0.1700
Data Index: 5990505 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4337. Min Range: -5.4337
Max Act: 5.0587. Min Act: -0.1700
Data Index: 3504263 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19