Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.4667. Min Act: -0.1700
Data Index: 5219095 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.3417. Min Act: -0.1700
Data Index: 762680 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.2792. Min Act: -0.1700
Data Index: 2427685 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.2792. Min Act: -0.1700
Data Index: 5009574 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.2167. Min Act: -0.1700
Data Index: 657069 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.1855. Min Act: -0.1700
Data Index: 8082042 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.1542. Min Act: -0.1700
Data Index: 5823603 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.1230. Min Act: -0.1700
Data Index: 7761825 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.0605. Min Act: -0.1700
Data Index: 1184825 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.0917. Min Act: -0.1700
Data Index: 8376887 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.0292. Min Act: -0.1700
Data Index: 932495 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4667. Min Range: -6.4667
Max Act: 5.9980. Min Act: -0.1700
Data Index: 1300041 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4667. Min Range: -6.4667
Max Act: 5.9980. Min Act: -0.1700
Data Index: 7150396 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4667. Min Range: -6.4667
Max Act: 5.9980. Min Act: -0.1700
Data Index: 1067806 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4667. Min Range: -6.4667
Max Act: 5.9980. Min Act: -0.1700
Data Index: 1126807 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4667. Min Range: -6.4667
Max Act: 5.9980. Min Act: -0.1700
Data Index: 7674083 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.0292. Min Act: -0.1700
Data Index: 5507703 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4667. Min Range: -6.4667
Max Act: 6.0292. Min Act: -0.1700
Data Index: 953493 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4667. Min Range: -6.4667
Max Act: 5.9980. Min Act: -0.1700
Data Index: 79144 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4667. Min Range: -6.4667
Max Act: 5.9355. Min Act: -0.1700
Data Index: 496723 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19