Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 123 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.8725. Min Act: -0.1700
Data Index: 7932674 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.5288. Min Act: -0.1700
Data Index: 4227262 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4975. Min Act: -0.1700
Data Index: 7259741 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4975. Min Act: -0.1700
Data Index: 8809683 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4350. Min Act: -0.1700
Data Index: 3552689 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4663. Min Act: -0.1700
Data Index: 5322516 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4038. Min Act: -0.1700
Data Index: 3292871 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.3725. Min Act: -0.1700
Data Index: 4505743 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.3725. Min Act: -0.1700
Data Index: 3859638 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.3100. Min Act: -0.1700
Data Index: 3278388 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.3100. Min Act: -0.1700
Data Index: 2154152 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.2788. Min Act: -0.1700
Data Index: 5892049 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.2788. Min Act: -0.1700
Data Index: 1339145 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.2475. Min Act: -0.1700
Data Index: 7865491 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.2163. Min Act: -0.1700
Data Index: 952008 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.2163. Min Act: -0.1700
Data Index: 314339 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.1538. Min Act: -0.1700
Data Index: 7292970 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.2163. Min Act: -0.1700
Data Index: 3776194 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.1538. Min Act: -0.1700
Data Index: 628059 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.1850. Min Act: -0.1700
Data Index: 7095051 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19