Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1460. Min Range: -7.1460
Max Act: 7.1460. Min Act: -0.1700
Data Index: 7085335 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1460. Min Range: -7.1460
Max Act: 7.1460. Min Act: -0.1700
Data Index: 1536083 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1460. Min Range: -7.1460
Max Act: 7.0835. Min Act: -0.1700
Data Index: 1536086 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.9898. Min Act: -0.1700
Data Index: 8676643 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1460. Min Range: -7.1460
Max Act: 7.0210. Min Act: -0.1700
Data Index: 5579230 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.9273. Min Act: -0.1700
Data Index: 5993478 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.8960. Min Act: -0.1700
Data Index: 6463323 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.8023. Min Act: -0.1700
Data Index: 8620568 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.8023. Min Act: -0.1700
Data Index: 3686687 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7710. Min Act: -0.1700
Data Index: 2204888 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7398. Min Act: -0.1700
Data Index: 3475467 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7710. Min Act: -0.1700
Data Index: 4045622 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7710. Min Act: -0.1700
Data Index: 2392451 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7398. Min Act: -0.1700
Data Index: 3291199 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7398. Min Act: -0.1700
Data Index: 5579227 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7398. Min Act: -0.1700
Data Index: 7970255 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7085. Min Act: -0.1700
Data Index: 1664888 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.7085. Min Act: -0.1700
Data Index: 2227857 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.6773. Min Act: -0.1700
Data Index: 8571398 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1460. Min Range: -7.1460
Max Act: 6.6460. Min Act: -0.1700
Data Index: 6761820 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19