Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4728 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.7128. Min Act: -0.1700
Data Index: 7318155 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.6503. Min Act: -0.1700
Data Index: 334692 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.5878. Min Act: -0.1700
Data Index: 6095171 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.5566. Min Act: -0.1700
Data Index: 3978126 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.4941. Min Act: -0.1700
Data Index: 3978124 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.4003. Min Act: -0.1700
Data Index: 990751 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.4003. Min Act: -0.1700
Data Index: 7620104 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.3378. Min Act: -0.1700
Data Index: 1418822 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.3691. Min Act: -0.1700
Data Index: 4601745 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.3691. Min Act: -0.1700
Data Index: 835281 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2753. Min Act: -0.1700
Data Index: 1320976 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.3066. Min Act: -0.1700
Data Index: 7994728 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2753. Min Act: -0.1700
Data Index: 2174573 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.3066. Min Act: -0.1700
Data Index: 7427337 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2753. Min Act: -0.1700
Data Index: 816407 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2753. Min Act: -0.1700
Data Index: 392076 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2441. Min Act: -0.1700
Data Index: 8184812 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2441. Min Act: -0.1700
Data Index: 633791 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2441. Min Act: -0.1700
Data Index: 2783689 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7128. Min Range: -5.7128
Max Act: 5.2441. Min Act: -0.1700
Data Index: 5394861 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19