Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4170 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.8144. Min Act: -0.1700
Data Index: 982601 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.8144. Min Act: -0.1700
Data Index: 3289093 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.6894. Min Act: -0.1700
Data Index: 5774336 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5019. Min Act: -0.1700
Data Index: 3464705 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5019. Min Act: -0.1700
Data Index: 542512 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5019. Min Act: -0.1700
Data Index: 308325 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5019. Min Act: -0.1700
Data Index: 4768922 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4706. Min Act: -0.1700
Data Index: 8486306 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5019. Min Act: -0.1700
Data Index: 4591542 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4706. Min Act: -0.1700
Data Index: 1991023 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4706. Min Act: -0.1700
Data Index: 7224353 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4706. Min Act: -0.1700
Data Index: 39465 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4706. Min Act: -0.1700
Data Index: 7089855 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4394. Min Act: -0.1700
Data Index: 2773053 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4394. Min Act: -0.1700
Data Index: 1991000 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4394. Min Act: -0.1700
Data Index: 492774 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4394. Min Act: -0.1700
Data Index: 2763163 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4394. Min Act: -0.1700
Data Index: 8430998 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4706. Min Act: -0.1700
Data Index: 2550185 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4081. Min Act: -0.1700
Data Index: 2555053 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19