Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.5566. Min Act: -0.1700
Data Index: 1380440 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.3691. Min Act: -0.1700
Data Index: 4920542 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.3066. Min Act: -0.1700
Data Index: 1101867 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.2441. Min Act: -0.1700
Data Index: 6646064 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.2441. Min Act: -0.1700
Data Index: 2737437 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.2441. Min Act: -0.1700
Data Index: 5535428 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.2129. Min Act: -0.1700
Data Index: 1831656 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.2129. Min Act: -0.1700
Data Index: 4918441 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.2441. Min Act: -0.1700
Data Index: 281166 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.2129. Min Act: -0.1700
Data Index: 5597881 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.1816. Min Act: -0.1700
Data Index: 6248027 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.1504. Min Act: -0.1700
Data Index: 2763972 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.1191. Min Act: -0.1700
Data Index: 3002569 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.0879. Min Act: -0.1700
Data Index: 1504331 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.1191. Min Act: -0.1700
Data Index: 8318563 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.0879. Min Act: -0.1700
Data Index: 5215635 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.0879. Min Act: -0.1700
Data Index: 1312265 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.0879. Min Act: -0.1700
Data Index: 6755180 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.0879. Min Act: -0.1700
Data Index: 2060389 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5566. Min Range: -6.5566
Max Act: 6.0879. Min Act: -0.1700
Data Index: 3403648 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19