Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.7636. Min Act: -0.1700
Data Index: 6501322 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.4199. Min Act: -0.1700
Data Index: 2916758 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.3261. Min Act: -0.1700
Data Index: 5413489 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.2636. Min Act: -0.1700
Data Index: 7802373 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.2011. Min Act: -0.1700
Data Index: 7942069 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.2324. Min Act: -0.1700
Data Index: 2900697 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.2011. Min Act: -0.1700
Data Index: 6043064 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.1699. Min Act: -0.1700
Data Index: 5047357 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.1699. Min Act: -0.1700
Data Index: 639132 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.1699. Min Act: -0.1700
Data Index: 3070860 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.1386. Min Act: -0.1700
Data Index: 2283152 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.1074. Min Act: -0.1700
Data Index: 4964955 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.0761. Min Act: -0.1700
Data Index: 3141211 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.0449. Min Act: -0.1700
Data Index: 2315632 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.0449. Min Act: -0.1700
Data Index: 6867805 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.0449. Min Act: -0.1700
Data Index: 1389828 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.0136. Min Act: -0.1700
Data Index: 887122 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.0136. Min Act: -0.1700
Data Index: 5002841 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7636. Min Range: -6.7636
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7659670 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7636. Min Range: -6.7636
Max Act: 5.9824. Min Act: -0.1700
Data Index: 2701680 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19