Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5253 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1709. Min Act: -0.1700
Data Index: 4741773 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1709. Min Act: -0.1700
Data Index: 3864765 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1084. Min Act: -0.1700
Data Index: 3547646 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.0459. Min Act: -0.1700
Data Index: 3262219 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.0459. Min Act: -0.1700
Data Index: 4438836 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9834. Min Act: -0.1700
Data Index: 7759636 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9834. Min Act: -0.1700
Data Index: 4527017 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9521. Min Act: -0.1700
Data Index: 6802051 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9521. Min Act: -0.1700
Data Index: 6282424 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9521. Min Act: -0.1700
Data Index: 3042487 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 1662656 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 415632 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 1352949 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 5869134 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 5409475 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 853217 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8896. Min Act: -0.1700
Data Index: 5889284 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8896. Min Act: -0.1700
Data Index: 5743806 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8896. Min Act: -0.1700
Data Index: 2482418 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8896. Min Act: -0.1700
Data Index: 6022285 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19