Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.4409. Min Act: -0.1700
Data Index: 42921 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.4247. Min Act: -0.1700
Data Index: 6555067 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3757. Min Act: -0.1700
Data Index: 5673721 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3757. Min Act: -0.1700
Data Index: 5673722 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3593. Min Act: -0.1700
Data Index: 5948244 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3593. Min Act: -0.1700
Data Index: 8470123 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3265. Min Act: -0.1700
Data Index: 177156 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3265. Min Act: -0.1700
Data Index: 1081142 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3101. Min Act: -0.1700
Data Index: 7494640 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3101. Min Act: -0.1700
Data Index: 6034067 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3101. Min Act: -0.1696
Data Index: 4624779 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3101. Min Act: -0.1698
Data Index: 4624778 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3101. Min Act: -0.1700
Data Index: 1551394 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3101. Min Act: -0.1602
Data Index: 42922 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.2937. Min Act: -0.1700
Data Index: 6555068 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.2937. Min Act: -0.1700
Data Index: 4584338 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.3101. Min Act: -0.1696
Data Index: 4624774 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.2937. Min Act: -0.1700
Data Index: 6054347 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.2772. Min Act: -0.1700
Data Index: 1081143 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4409. Min Range: -2.4409
Max Act: 2.2772. Min Act: -0.1700
Data Index: 1318300 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19