Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 725 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.9687. Min Act: -0.1700
Data Index: 3616222 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.7500. Min Act: -0.1700
Data Index: 7138205 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.6250. Min Act: -0.1700
Data Index: 1833441 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.3750. Min Act: -0.1700
Data Index: 2479023 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.3437. Min Act: -0.1700
Data Index: 303645 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.3125. Min Act: -0.1700
Data Index: 8577272 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2812. Min Act: -0.1700
Data Index: 3091286 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2812. Min Act: -0.1700
Data Index: 2320380 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2812. Min Act: -0.1700
Data Index: 6096291 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2500. Min Act: -0.1700
Data Index: 2690471 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2500. Min Act: -0.1700
Data Index: 3817602 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2500. Min Act: -0.1700
Data Index: 7747515 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2187. Min Act: -0.1700
Data Index: 5164106 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.2500. Min Act: -0.1700
Data Index: 1156480 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.1562. Min Act: -0.1700
Data Index: 5603016 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.1875. Min Act: -0.1700
Data Index: 1031489 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.1562. Min Act: -0.1700
Data Index: 7292745 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.1875. Min Act: -0.1700
Data Index: 5075081 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.1562. Min Act: -0.1700
Data Index: 8002950 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9687. Min Range: -6.9687
Max Act: 6.1562. Min Act: -0.1700
Data Index: 5117432 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19