Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1063 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.4050. Min Act: -0.1700
Data Index: 3980588 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.2488. Min Act: -0.1700
Data Index: 367068 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.2175. Min Act: -0.1700
Data Index: 7601105 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.1863. Min Act: -0.1700
Data Index: 5554343 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.1238. Min Act: -0.1700
Data Index: 8769235 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.0613. Min Act: -0.1700
Data Index: 3022552 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.0613. Min Act: -0.1700
Data Index: 3095581 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.0300. Min Act: -0.1700
Data Index: 2715838 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.9988. Min Act: -0.1700
Data Index: 5778975 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.9988. Min Act: -0.1700
Data Index: 1044034 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4050. Min Range: -5.4050
Max Act: 5.0300. Min Act: -0.1700
Data Index: 526158 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.9363. Min Act: -0.1700
Data Index: 8630740 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.9363. Min Act: -0.1700
Data Index: 3400638 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.9050. Min Act: -0.1700
Data Index: 6468090 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.8738. Min Act: -0.1700
Data Index: 180857 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.8738. Min Act: -0.1700
Data Index: 5716461 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.8738. Min Act: -0.1700
Data Index: 1571605 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.9050. Min Act: -0.1700
Data Index: 321436 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.8425. Min Act: -0.1700
Data Index: 8390082 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4050. Min Range: -5.4050
Max Act: 4.8113. Min Act: -0.1700
Data Index: 1648572 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19