Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1299 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2186. Min Range: -8.2186
Max Act: 8.2186. Min Act: -0.1700
Data Index: 7252805 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2186. Min Range: -8.2186
Max Act: 8.2186. Min Act: -0.1700
Data Index: 3857640 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2186. Min Range: -8.2186
Max Act: 8.2186. Min Act: -0.1700
Data Index: 6048628 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2186. Min Range: -8.2186
Max Act: 8.0311. Min Act: -0.1700
Data Index: 652131 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2186. Min Range: -8.2186
Max Act: 8.0311. Min Act: -0.1700
Data Index: 3284251 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2186. Min Range: -8.2186
Max Act: 8.0311. Min Act: -0.1700
Data Index: 2901839 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2186. Min Range: -8.2186
Max Act: 8.0311. Min Act: -0.1700
Data Index: 2939144 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.9686. Min Act: -0.1700
Data Index: 1017131 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.9686. Min Act: -0.1700
Data Index: 4044554 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.9686. Min Act: -0.1700
Data Index: 2153322 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.9686. Min Act: -0.1700
Data Index: 1130391 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.9686. Min Act: -0.1700
Data Index: 4153410 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.9061. Min Act: -0.1700
Data Index: 7704885 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.8436. Min Act: -0.1700
Data Index: 2050378 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.8436. Min Act: -0.1700
Data Index: 2623859 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.8436. Min Act: -0.1700
Data Index: 7903868 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.8436. Min Act: -0.1700
Data Index: 1982745 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.7811. Min Act: -0.1700
Data Index: 1805059 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.7811. Min Act: -0.1700
Data Index: 4650084 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2186. Min Range: -8.2186
Max Act: 7.7811. Min Act: -0.1700
Data Index: 5167306 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19