Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1395 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5675. Min Range: -5.5675
Max Act: 5.5675. Min Act: -0.1700
Data Index: 2261230 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5675. Min Range: -5.5675
Max Act: 5.1925. Min Act: -0.1700
Data Index: 7161504 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5675. Min Range: -5.5675
Max Act: 5.1300. Min Act: -0.1700
Data Index: 7161503 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5675. Min Range: -5.5675
Max Act: 5.0987. Min Act: -0.1700
Data Index: 6619370 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5675. Min Range: -5.5675
Max Act: 5.0675. Min Act: -0.1700
Data Index: 1715083 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5675. Min Range: -5.5675
Max Act: 5.0362. Min Act: -0.1700
Data Index: 8681760 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5675. Min Range: -5.5675
Max Act: 5.0050. Min Act: -0.1700
Data Index: 7161505 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.9737. Min Act: -0.1700
Data Index: 237145 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.9112. Min Act: -0.1700
Data Index: 4019266 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.9112. Min Act: -0.1700
Data Index: 2230465 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.8800. Min Act: -0.1700
Data Index: 3669140 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.8175. Min Act: -0.1700
Data Index: 8465390 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.8175. Min Act: -0.1700
Data Index: 3174854 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.8175. Min Act: -0.1700
Data Index: 7091562 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.7862. Min Act: -0.1696
Data Index: 237146 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.7550. Min Act: -0.1700
Data Index: 4585540 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 4689447 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.7237. Min Act: -0.1700
Data Index: 3833745 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 6167459 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5675. Min Range: -5.5675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 4800382 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19