Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0174. Min Range: -7.0174
Max Act: 7.0174. Min Act: -0.1700
Data Index: 1131678 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.9236. Min Act: -0.1700
Data Index: 8094115 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.8611. Min Act: -0.1700
Data Index: 6760332 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.7674. Min Act: -0.1700
Data Index: 7441936 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.7361. Min Act: -0.1700
Data Index: 3345582 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.7361. Min Act: -0.1700
Data Index: 2018632 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.7049. Min Act: -0.1700
Data Index: 5937786 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.7049. Min Act: -0.1700
Data Index: 6465986 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6424. Min Act: -0.1700
Data Index: 4014033 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6424. Min Act: -0.1700
Data Index: 8316731 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6424. Min Act: -0.1700
Data Index: 2040141 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6111. Min Act: -0.1700
Data Index: 2756028 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6424. Min Act: -0.1700
Data Index: 7747292 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6424. Min Act: -0.1700
Data Index: 1092628 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6111. Min Act: -0.1700
Data Index: 1556387 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5799. Min Act: -0.1700
Data Index: 6389068 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5799. Min Act: -0.1700
Data Index: 1264298 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5799. Min Act: -0.1700
Data Index: 1400153 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5486. Min Act: -0.1700
Data Index: 7098402 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5486. Min Act: -0.1700
Data Index: 6300211 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19