Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6362 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1781. Min Range: -8.1781
Max Act: 8.1781. Min Act: -0.1700
Data Index: 2107401 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.8656. Min Act: -0.1700
Data Index: 932320 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.7719. Min Act: -0.1700
Data Index: 7695448 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.7719. Min Act: -0.1700
Data Index: 7381974 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.7406. Min Act: -0.1700
Data Index: 2412097 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.6469. Min Act: -0.1700
Data Index: 6321304 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.6469. Min Act: -0.1700
Data Index: 5451976 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5844. Min Act: -0.1700
Data Index: 151199 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5844. Min Act: -0.1700
Data Index: 2734431 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5844. Min Act: -0.1700
Data Index: 5856864 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5531. Min Act: -0.1700
Data Index: 7267378 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5531. Min Act: -0.1700
Data Index: 5987372 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5219. Min Act: -0.1700
Data Index: 187247 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4906. Min Act: -0.1700
Data Index: 2084613 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4594. Min Act: -0.1700
Data Index: 1845970 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4281. Min Act: -0.1700
Data Index: 4346743 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.3969. Min Act: -0.1700
Data Index: 6009897 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.3969. Min Act: -0.1700
Data Index: 7691413 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.3969. Min Act: -0.1700
Data Index: 7899554 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.2719. Min Act: -0.1700
Data Index: 2580646 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19