Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1450 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0345. Min Range: -5.0345
Max Act: 5.0345. Min Act: -0.1700
Data Index: 7942499 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.9720. Min Act: -0.1700
Data Index: 2822513 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.9407. Min Act: -0.1700
Data Index: 8602639 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.9095. Min Act: -0.1700
Data Index: 5107798 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.8782. Min Act: -0.1700
Data Index: 448408 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.8470. Min Act: -0.1700
Data Index: 96974 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.8470. Min Act: -0.1700
Data Index: 13538 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.8157. Min Act: -0.1700
Data Index: 6445567 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.8157. Min Act: -0.1700
Data Index: 5651784 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.8157. Min Act: -0.1700
Data Index: 2834106 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7845. Min Act: -0.1700
Data Index: 1327922 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7845. Min Act: -0.1700
Data Index: 7907494 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7532. Min Act: -0.1700
Data Index: 2275915 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7532. Min Act: -0.1700
Data Index: 6823260 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7532. Min Act: -0.1700
Data Index: 5728306 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7532. Min Act: -0.1700
Data Index: 7505999 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7532. Min Act: -0.1700
Data Index: 2529281 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7532. Min Act: -0.1700
Data Index: 4902586 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7220. Min Act: -0.1700
Data Index: 2195134 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0345. Min Range: -5.0345
Max Act: 4.7220. Min Act: -0.1700
Data Index: 7159876 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19