Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.7911. Min Act: -0.1700
Data Index: 4063223 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.7286. Min Act: -0.1700
Data Index: 6949378 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.6661. Min Act: -0.1700
Data Index: 2331139 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.6661. Min Act: -0.1700
Data Index: 502328 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.5411. Min Act: -0.1700
Data Index: 6029102 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 7474898 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 1991188 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 3344372 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 5145925 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 820794 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 452624 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 7362563 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4161. Min Act: -0.1700
Data Index: 16386 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4161. Min Act: -0.1700
Data Index: 2415469 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4786. Min Act: -0.1700
Data Index: 694627 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4161. Min Act: -0.1700
Data Index: 5351997 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.4161. Min Act: -0.1700
Data Index: 112670 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.3536. Min Act: -0.1700
Data Index: 3301284 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.3536. Min Act: -0.1700
Data Index: 3592811 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7911. Min Range: -8.7911
Max Act: 8.3536. Min Act: -0.1700
Data Index: 2040893 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19