Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5205 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.5189. Min Act: -0.1700
Data Index: 1888134 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.5501. Min Act: -0.1700
Data Index: 1915579 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.5189. Min Act: -0.1700
Data Index: 4646757 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.4876. Min Act: -0.1700
Data Index: 6080597 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.4876. Min Act: -0.1700
Data Index: 8503843 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.5189. Min Act: -0.1700
Data Index: 8328372 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.4876. Min Act: -0.1700
Data Index: 671844 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.4876. Min Act: -0.1700
Data Index: 2928854 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.4251. Min Act: -0.1700
Data Index: 5813404 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.4251. Min Act: -0.1700
Data Index: 7089243 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.3939. Min Act: -0.1700
Data Index: 3062852 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.3939. Min Act: -0.1700
Data Index: 3911275 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.3626. Min Act: -0.1700
Data Index: 860928 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.3626. Min Act: -0.1700
Data Index: 702350 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.3314. Min Act: -0.1700
Data Index: 1760204 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.3314. Min Act: -0.1700
Data Index: 1278207 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.2689. Min Act: -0.1700
Data Index: 5019009 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.3001. Min Act: -0.1700
Data Index: 1512289 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.2689. Min Act: -0.1700
Data Index: 3011506 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5501. Min Range: -6.5501
Max Act: 6.2689. Min Act: -0.1700
Data Index: 554930 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19