Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4796 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.2665. Min Act: -0.1700
Data Index: 7289450 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.2040. Min Act: -0.1700
Data Index: 6311124 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.1102. Min Act: -0.1700
Data Index: 448558 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0789. Min Act: -0.1700
Data Index: 2640564 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.9852. Min Act: -0.1700
Data Index: 669974 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.9852. Min Act: -0.1700
Data Index: 6455432 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.9852. Min Act: -0.1700
Data Index: 6546413 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.9539. Min Act: -0.1700
Data Index: 4331697 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8914. Min Act: -0.1700
Data Index: 3523285 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8914. Min Act: -0.1700
Data Index: 6119255 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8914. Min Act: -0.1700
Data Index: 2495625 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8914. Min Act: -0.1700
Data Index: 5063424 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8601. Min Act: -0.1700
Data Index: 8759452 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8601. Min Act: -0.1700
Data Index: 6889505 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8601. Min Act: -0.1700
Data Index: 2489082 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8601. Min Act: -0.1700
Data Index: 6511758 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8288. Min Act: -0.1700
Data Index: 1694519 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.8601. Min Act: -0.1700
Data Index: 4930832 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.7976. Min Act: -0.1700
Data Index: 4128878 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.7976. Min Act: -0.1700
Data Index: 2466278 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19