Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2533 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7790. Min Range: -8.7790
Max Act: 8.7790. Min Act: -0.1700
Data Index: 4398461 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7790. Min Range: -8.7790
Max Act: 8.4665. Min Act: -0.1700
Data Index: 1875506 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.8728. Min Act: -0.1700
Data Index: 4662273 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.6540. Min Act: -0.1700
Data Index: 8285857 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.5915. Min Act: -0.1700
Data Index: 8285863 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.4978. Min Act: -0.1700
Data Index: 6496678 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.4665. Min Act: -0.1700
Data Index: 2987882 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.4040. Min Act: -0.1700
Data Index: 4201495 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.3415. Min Act: -0.1700
Data Index: 4439171 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.3103. Min Act: -0.1700
Data Index: 401029 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.3103. Min Act: -0.1700
Data Index: 1600391 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.2478. Min Act: -0.1700
Data Index: 4263636 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.2478. Min Act: -0.1700
Data Index: 3064174 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.2478. Min Act: -0.1700
Data Index: 3627366 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.1540. Min Act: -0.1700
Data Index: 5558579 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.1540. Min Act: -0.1700
Data Index: 1589093 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.1540. Min Act: -0.1700
Data Index: 1589092 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.1540. Min Act: -0.1700
Data Index: 764326 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.1228. Min Act: -0.1700
Data Index: 3684406 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7790. Min Range: -8.7790
Max Act: 7.1228. Min Act: -0.1700
Data Index: 2370180 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19