Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.9612. Min Act: -0.1700
Data Index: 5773864 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.5862. Min Act: -0.1700
Data Index: 1382601 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.4612. Min Act: -0.1700
Data Index: 8320010 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.3987. Min Act: -0.1700
Data Index: 5408400 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.3050. Min Act: -0.1700
Data Index: 3352897 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.2737. Min Act: -0.1700
Data Index: 4624021 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.2112. Min Act: -0.1700
Data Index: 1873105 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.1800. Min Act: -0.1700
Data Index: 5898452 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.1800. Min Act: -0.1700
Data Index: 4997810 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.1487. Min Act: -0.1700
Data Index: 3069875 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.1175. Min Act: -0.1700
Data Index: 3699740 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.0550. Min Act: -0.1700
Data Index: 5403823 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.0862. Min Act: -0.1700
Data Index: 5064484 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.0237. Min Act: -0.1700
Data Index: 6804841 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.0237. Min Act: -0.1700
Data Index: 7920193 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9612. Min Range: -7.9612
Max Act: 6.9612. Min Act: -0.1700
Data Index: 3848730 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9612. Min Range: -7.9612
Max Act: 7.0237. Min Act: -0.1700
Data Index: 7671908 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9612. Min Range: -7.9612
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4212246 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9612. Min Range: -7.9612
Max Act: 6.9612. Min Act: -0.1700
Data Index: 6625707 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9612. Min Range: -7.9612
Max Act: 6.9300. Min Act: -0.1700
Data Index: 5753571 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19