Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5768 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0776. Min Range: -9.0776
Max Act: 9.0776. Min Act: -0.1700
Data Index: 4917026 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.9526. Min Act: -0.1700
Data Index: 4502527 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.7026. Min Act: -0.1700
Data Index: 4267077 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.7026. Min Act: -0.1700
Data Index: 5778687 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.6401. Min Act: -0.1700
Data Index: 2496792 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.5776. Min Act: -0.1700
Data Index: 6085888 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.5776. Min Act: -0.1700
Data Index: 4431218 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.4526. Min Act: -0.1700
Data Index: 2870901 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.5151. Min Act: -0.1700
Data Index: 2564141 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.4526. Min Act: -0.1700
Data Index: 8017503 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.4526. Min Act: -0.1700
Data Index: 7706876 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.4526. Min Act: -0.1700
Data Index: 5216016 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.5151. Min Act: -0.1700
Data Index: 5886395 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.3901. Min Act: -0.1700
Data Index: 8396844 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.3901. Min Act: -0.1700
Data Index: 3821853 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.3901. Min Act: -0.1700
Data Index: 2535852 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.3901. Min Act: -0.1700
Data Index: 8674465 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.3276. Min Act: -0.1700
Data Index: 350615 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.3276. Min Act: -0.1700
Data Index: 4705396 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0776. Min Range: -9.0776
Max Act: 8.3276. Min Act: -0.1700
Data Index: 3407748 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19