Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4289 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.7540. Min Act: -0.1700
Data Index: 800019 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.6915. Min Act: -0.1700
Data Index: 8121601 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.5977. Min Act: -0.1700
Data Index: 1351622 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.5040. Min Act: -0.1700
Data Index: 6216320 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.4415. Min Act: -0.1700
Data Index: 3744000 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.4415. Min Act: -0.1700
Data Index: 2323570 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.4415. Min Act: -0.1700
Data Index: 414056 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.4102. Min Act: -0.1700
Data Index: 8208122 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3790. Min Act: -0.1700
Data Index: 8048758 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3790. Min Act: -0.1700
Data Index: 2261943 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3790. Min Act: -0.1700
Data Index: 353034 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3790. Min Act: -0.1700
Data Index: 153356 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3790. Min Act: -0.1700
Data Index: 7751776 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3477. Min Act: -0.1700
Data Index: 6786172 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3477. Min Act: -0.1700
Data Index: 1846411 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.2852. Min Act: -0.1700
Data Index: 4403381 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.3165. Min Act: -0.1700
Data Index: 300681 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.2852. Min Act: -0.1700
Data Index: 1920285 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.2852. Min Act: -0.1700
Data Index: 1343430 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7540. Min Range: -5.7540
Max Act: 5.2852. Min Act: -0.1700
Data Index: 5706827 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19