Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1529 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0694. Min Range: -4.0694
Max Act: 4.0694. Min Act: -0.1700
Data Index: 1095070 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.8818. Min Act: -0.1700
Data Index: 8596856 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.8506. Min Act: -0.1700
Data Index: 7724035 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.8037. Min Act: -0.1700
Data Index: 2839181 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7255. Min Act: -0.1700
Data Index: 6854226 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6629. Min Act: -0.1700
Data Index: 8457395 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6472. Min Act: -0.1700
Data Index: 1353354 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6159. Min Act: -0.1700
Data Index: 7251560 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6159. Min Act: -0.1700
Data Index: 6321191 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6159. Min Act: -0.1700
Data Index: 912313 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6003. Min Act: -0.1700
Data Index: 7763060 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.5533. Min Act: -0.1700
Data Index: 338162 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.5377. Min Act: -0.1700
Data Index: 4615993 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.5064. Min Act: -0.1700
Data Index: 3831893 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.5064. Min Act: -0.1700
Data Index: 7654871 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.4907. Min Act: -0.1700
Data Index: 3592340 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.4907. Min Act: -0.1700
Data Index: 4039405 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.4907. Min Act: -0.1700
Data Index: 5006694 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.4594. Min Act: -0.1700
Data Index: 729938 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.4437. Min Act: -0.1700
Data Index: 3486467 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19