Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3861 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0437. Min Range: -6.0437
Max Act: 6.0437. Min Act: -0.1700
Data Index: 662896 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.6062. Min Act: -0.1700
Data Index: 7655499 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5125. Min Act: -0.1700
Data Index: 1316558 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5125. Min Act: -0.1700
Data Index: 6126801 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4812. Min Act: -0.1700
Data Index: 3574266 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4812. Min Act: -0.1700
Data Index: 6496046 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5125. Min Act: -0.1700
Data Index: 223160 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4812. Min Act: -0.1700
Data Index: 5623395 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4500. Min Act: -0.1700
Data Index: 6263463 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4500. Min Act: -0.1700
Data Index: 7295372 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4500. Min Act: -0.1700
Data Index: 4263902 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4187. Min Act: -0.1700
Data Index: 7233867 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.3875. Min Act: -0.1700
Data Index: 2128489 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.3562. Min Act: -0.1700
Data Index: 1045958 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.3562. Min Act: -0.1700
Data Index: 2202222 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.3250. Min Act: -0.1700
Data Index: 5710851 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.3250. Min Act: -0.1700
Data Index: 3792037 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.2937. Min Act: -0.1700
Data Index: 4487088 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.2937. Min Act: -0.1700
Data Index: 4822347 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.2625. Min Act: -0.1700
Data Index: 2984455 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19