Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.3125. Min Act: -0.1700
Data Index: 786423 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.2500. Min Act: -0.1700
Data Index: 3331352 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3125. Min Range: -8.3125
Max Act: 8.0625. Min Act: -0.1700
Data Index: 5889459 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.9062. Min Act: -0.1700
Data Index: 1395385 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7500. Min Act: -0.1700
Data Index: 2691759 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7812. Min Act: -0.1700
Data Index: 8492577 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7187. Min Act: -0.1700
Data Index: 1656490 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6875. Min Act: -0.1700
Data Index: 7620751 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7187. Min Act: -0.1700
Data Index: 8481392 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7187. Min Act: -0.1700
Data Index: 3292186 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.7187. Min Act: -0.1700
Data Index: 3880900 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6875. Min Act: -0.1700
Data Index: 401181 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6562. Min Act: -0.1700
Data Index: 3568927 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6250. Min Act: -0.1700
Data Index: 3706540 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6250. Min Act: -0.1700
Data Index: 969063 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6250. Min Act: -0.1700
Data Index: 3786439 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6250. Min Act: -0.1700
Data Index: 3478763 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.5937. Min Act: -0.1700
Data Index: 4873358 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.6250. Min Act: -0.1700
Data Index: 6906539 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3125. Min Range: -8.3125
Max Act: 7.5937. Min Act: -0.1700
Data Index: 3723568 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19