Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4909 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.6954. Min Act: -0.1700
Data Index: 1675560 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.6017. Min Act: -0.1700
Data Index: 2375523 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.5704. Min Act: -0.1700
Data Index: 3626280 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.5392. Min Act: -0.1700
Data Index: 8762167 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.5392. Min Act: -0.1700
Data Index: 5055326 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.5704. Min Act: -0.1700
Data Index: 238742 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.5079. Min Act: -0.1700
Data Index: 1024408 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.4767. Min Act: -0.1700
Data Index: 1531737 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.4142. Min Act: -0.1700
Data Index: 231733 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3829. Min Act: -0.1700
Data Index: 5532492 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.4142. Min Act: -0.1700
Data Index: 5862445 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.4142. Min Act: -0.1700
Data Index: 8006908 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3829. Min Act: -0.1700
Data Index: 8338234 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3517. Min Act: -0.1700
Data Index: 1451697 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3517. Min Act: -0.1700
Data Index: 7935246 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3517. Min Act: -0.1700
Data Index: 3561648 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3204. Min Act: -0.1700
Data Index: 1001471 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3204. Min Act: -0.1700
Data Index: 7260764 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3204. Min Act: -0.1700
Data Index: 6928089 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6954. Min Range: -5.6954
Max Act: 5.3204. Min Act: -0.1700
Data Index: 2082016 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19