Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.3361. Min Act: -0.1700
Data Index: 1432852 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.3048. Min Act: -0.1700
Data Index: 7517114 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.3048. Min Act: -0.1700
Data Index: 5632824 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.3048. Min Act: -0.1700
Data Index: 3453337 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.1798. Min Act: -0.1700
Data Index: 2664225 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.1486. Min Act: -0.1700
Data Index: 8557403 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.1486. Min Act: -0.1700
Data Index: 5935293 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.1173. Min Act: -0.1700
Data Index: 3279637 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.1173. Min Act: -0.1700
Data Index: 5146159 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.0861. Min Act: -0.1700
Data Index: 8713882 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.0548. Min Act: -0.1700
Data Index: 536474 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.0548. Min Act: -0.1700
Data Index: 5538596 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.0236. Min Act: -0.1700
Data Index: 1884110 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3361. Min Range: -5.3361
Max Act: 5.0236. Min Act: -0.1700
Data Index: 7307484 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3361. Min Range: -5.3361
Max Act: 4.9923. Min Act: -0.1700
Data Index: 7512614 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3361. Min Range: -5.3361
Max Act: 4.9923. Min Act: -0.1700
Data Index: 722985 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3361. Min Range: -5.3361
Max Act: 4.9611. Min Act: -0.1700
Data Index: 913867 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3361. Min Range: -5.3361
Max Act: 4.9923. Min Act: -0.1700
Data Index: 6221552 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3361. Min Range: -5.3361
Max Act: 4.9611. Min Act: -0.1700
Data Index: 6224390 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3361. Min Range: -5.3361
Max Act: 4.9611. Min Act: -0.1700
Data Index: 2106355 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19