Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1439 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0016. Min Range: -9.0016
Max Act: 9.0016. Min Act: -0.1700
Data Index: 5000803 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.4391. Min Act: -0.1700
Data Index: 2824608 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.2516. Min Act: -0.1700
Data Index: 3196717 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.1266. Min Act: -0.1700
Data Index: 3260914 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.1266. Min Act: -0.1700
Data Index: 6102811 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.1266. Min Act: -0.1700
Data Index: 450611 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.1891. Min Act: -0.1700
Data Index: 6798078 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.1266. Min Act: -0.1700
Data Index: 295306 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.0641. Min Act: -0.1699
Data Index: 387416 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.0641. Min Act: -0.1700
Data Index: 4935418 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.0016. Min Act: -0.1700
Data Index: 7715520 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0016. Min Range: -9.0016
Max Act: 8.0016. Min Act: -0.1700
Data Index: 8174472 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.9391. Min Act: -0.1700
Data Index: 6915693 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.9391. Min Act: -0.1700
Data Index: 3612750 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.9391. Min Act: -0.1700
Data Index: 7047432 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.9391. Min Act: -0.1700
Data Index: 1382911 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.8766. Min Act: -0.1690
Data Index: 2216207 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.8141. Min Act: -0.1700
Data Index: 2076829 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.8141. Min Act: -0.1700
Data Index: 1320028 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0016. Min Range: -9.0016
Max Act: 7.7516. Min Act: -0.1700
Data Index: 451190 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19