Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.7131. Min Act: -0.1700
Data Index: 2794216 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.6193. Min Act: -0.1700
Data Index: 7093274 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.5568. Min Act: -0.1700
Data Index: 711758 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.5568. Min Act: -0.1700
Data Index: 4266430 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 3354114 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4943. Min Act: -0.1700
Data Index: 8099848 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4006. Min Act: -0.1700
Data Index: 7327202 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3381. Min Act: -0.1700
Data Index: 559039 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3068. Min Act: -0.1700
Data Index: 1717079 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2443. Min Act: -0.1700
Data Index: 1464993 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2443. Min Act: -0.1700
Data Index: 4484860 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2443. Min Act: -0.1700
Data Index: 3616414 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2443. Min Act: -0.1700
Data Index: 344896 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 8043934 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 3088536 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 18228 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 6515939 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 1698909 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 5106572 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1506. Min Act: -0.1700
Data Index: 7173691 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19