Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2202. Min Range: -8.2202
Max Act: 8.2202. Min Act: -0.1700
Data Index: 4515186 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2202. Min Range: -8.2202
Max Act: 8.2202. Min Act: -0.1700
Data Index: 7357900 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.9702. Min Act: -0.1700
Data Index: 1560916 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.9702. Min Act: -0.1700
Data Index: 1560918 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.9077. Min Act: -0.1700
Data Index: 7357901 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.8452. Min Act: -0.1700
Data Index: 1560917 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.7827. Min Act: -0.1700
Data Index: 2883069 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.7827. Min Act: -0.1700
Data Index: 4252587 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.7202. Min Act: -0.1700
Data Index: 5416549 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.7202. Min Act: -0.1700
Data Index: 4406780 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.7202. Min Act: -0.1700
Data Index: 5775175 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.6577. Min Act: -0.1700
Data Index: 5775172 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.6577. Min Act: -0.1700
Data Index: 4252591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.6265. Min Act: -0.1700
Data Index: 5076822 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.5952. Min Act: -0.1700
Data Index: 2844469 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.5640. Min Act: -0.1700
Data Index: 1634360 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.5640. Min Act: -0.1700
Data Index: 4515185 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.5640. Min Act: -0.1700
Data Index: 7238262 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.5327. Min Act: -0.1700
Data Index: 2445887 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2202. Min Range: -8.2202
Max Act: 7.5015. Min Act: -0.1700
Data Index: 6320538 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19