Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.4375. Min Act: -0.1700
Data Index: 5275411 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.4062. Min Act: -0.1700
Data Index: 8533979 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.3125. Min Act: -0.1700
Data Index: 5533026 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.3125. Min Act: -0.1700
Data Index: 7820176 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.2812. Min Act: -0.1700
Data Index: 4685870 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1875. Min Act: -0.1700
Data Index: 3746900 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1562. Min Act: -0.1700
Data Index: 2417183 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1875. Min Act: -0.1700
Data Index: 100204 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1562. Min Act: -0.1700
Data Index: 8384570 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1562. Min Act: -0.1700
Data Index: 630741 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1562. Min Act: -0.1700
Data Index: 2425642 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1562. Min Act: -0.1700
Data Index: 5994180 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1562. Min Act: -0.1700
Data Index: 5039711 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1250. Min Act: -0.1700
Data Index: 3426450 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1562. Min Act: -0.1700
Data Index: 209084 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1250. Min Act: -0.1700
Data Index: 3607559 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1250. Min Act: -0.1700
Data Index: 7266444 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1250. Min Act: -0.1700
Data Index: 601308 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1250. Min Act: -0.1700
Data Index: 3746899 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4375. Min Range: -5.4375
Max Act: 5.1250. Min Act: -0.1700
Data Index: 3032833 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19