Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4250 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.7881. Min Act: -0.1700
Data Index: 3491240 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.6006. Min Act: -0.1700
Data Index: 2439412 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.6319. Min Act: -0.1700
Data Index: 4874273 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.3819. Min Act: -0.1700
Data Index: 5437304 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.3194. Min Act: -0.1700
Data Index: 7921986 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2881. Min Act: -0.1700
Data Index: 6415911 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2256. Min Act: -0.1700
Data Index: 6782531 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2256. Min Act: -0.1700
Data Index: 7422734 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2256. Min Act: -0.1700
Data Index: 7877427 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1944. Min Act: -0.1700
Data Index: 3843785 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1944. Min Act: -0.1700
Data Index: 470922 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 4894034 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 5088210 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 1775469 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 594148 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.0694. Min Act: -0.1700
Data Index: 587241 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.0381. Min Act: -0.1700
Data Index: 5275047 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.0381. Min Act: -0.1700
Data Index: 1878328 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.0381. Min Act: -0.1700
Data Index: 6611124 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.0069. Min Act: -0.1700
Data Index: 6608992 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19