Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4528 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.6603. Min Act: -0.1700
Data Index: 4390807 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.4728. Min Act: -0.1700
Data Index: 4777696 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.3790. Min Act: -0.1700
Data Index: 7855091 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.2853. Min Act: -0.1700
Data Index: 4120234 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.2228. Min Act: -0.1700
Data Index: 2908846 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.1290. Min Act: -0.1700
Data Index: 6983472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.1603. Min Act: -0.1700
Data Index: 2502730 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.1290. Min Act: -0.1700
Data Index: 3163133 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.1290. Min Act: -0.1700
Data Index: 4159876 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.1290. Min Act: -0.1700
Data Index: 6020854 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0978. Min Act: -0.1700
Data Index: 8624011 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0978. Min Act: -0.1700
Data Index: 636195 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0978. Min Act: -0.1700
Data Index: 6996364 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0665. Min Act: -0.1700
Data Index: 7233403 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0665. Min Act: -0.1700
Data Index: 7456602 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0353. Min Act: -0.1700
Data Index: 251930 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0665. Min Act: -0.1700
Data Index: 4682867 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0353. Min Act: -0.1700
Data Index: 1770889 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0040. Min Act: -0.1700
Data Index: 7449809 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6603. Min Range: -7.6603
Max Act: 7.0040. Min Act: -0.1700
Data Index: 4151105 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19