Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.4030. Min Act: -0.1700
Data Index: 675622 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.3718. Min Act: -0.1700
Data Index: 5727437 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.2468. Min Act: -0.1700
Data Index: 4558093 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.1530. Min Act: -0.1700
Data Index: 1287613 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.1218. Min Act: -0.1700
Data Index: 6372529 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.1218. Min Act: -0.1700
Data Index: 6586773 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.1218. Min Act: -0.1700
Data Index: 1395244 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0905. Min Act: -0.1700
Data Index: 4788589 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0905. Min Act: -0.1700
Data Index: 5288793 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0905. Min Act: -0.1700
Data Index: 8663160 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0593. Min Act: -0.1700
Data Index: 3957945 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0905. Min Act: -0.1700
Data Index: 4500905 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0280. Min Act: -0.1700
Data Index: 7201444 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0593. Min Act: -0.1700
Data Index: 8054030 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0905. Min Act: -0.1700
Data Index: 3148874 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0593. Min Act: -0.1700
Data Index: 5554946 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0280. Min Act: -0.1700
Data Index: 6732229 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0905. Min Act: -0.1700
Data Index: 897008 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4030. Min Range: -5.4030
Max Act: 4.9968. Min Act: -0.1700
Data Index: 3371671 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4030. Min Range: -5.4030
Max Act: 5.0280. Min Act: -0.1700
Data Index: 6773825 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19