Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 553 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.7817. Min Act: -0.1700
Data Index: 5650013 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.6879. Min Act: -0.1700
Data Index: 2296637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.6254. Min Act: -0.1700
Data Index: 212852 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.6567. Min Act: -0.1700
Data Index: 1817504 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.5317. Min Act: -0.1700
Data Index: 5935184 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.5629. Min Act: -0.1700
Data Index: 4224314 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.5004. Min Act: -0.1700
Data Index: 1280796 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.4692. Min Act: -0.1700
Data Index: 4405032 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.4379. Min Act: -0.1700
Data Index: 4675932 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.4692. Min Act: -0.1700
Data Index: 6181999 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.4379. Min Act: -0.1700
Data Index: 5444433 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.3754. Min Act: -0.1700
Data Index: 8316116 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.4067. Min Act: -0.1700
Data Index: 7966684 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.4067. Min Act: -0.1700
Data Index: 2444826 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.3754. Min Act: -0.1700
Data Index: 7173803 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.3754. Min Act: -0.1700
Data Index: 2483920 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.3442. Min Act: -0.1700
Data Index: 3534445 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.3754. Min Act: -0.1700
Data Index: 7115238 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.3754. Min Act: -0.1700
Data Index: 2849366 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7817. Min Range: -5.7817
Max Act: 5.3442. Min Act: -0.1700
Data Index: 3967786 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19