Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5369 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.4857. Min Act: -0.1700
Data Index: 7540005 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.4857. Min Act: -0.1700
Data Index: 1806563 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.3919. Min Act: -0.1700
Data Index: 4054475 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.3607. Min Act: -0.1700
Data Index: 1586256 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.3294. Min Act: -0.1700
Data Index: 2215133 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.3294. Min Act: -0.1700
Data Index: 2500531 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.2669. Min Act: -0.1700
Data Index: 4143818 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.2669. Min Act: -0.1700
Data Index: 994563 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.2357. Min Act: -0.1700
Data Index: 5082078 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.1732. Min Act: -0.1700
Data Index: 8189527 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.2044. Min Act: -0.1700
Data Index: 3664524 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.1732. Min Act: -0.1700
Data Index: 3102746 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.1419. Min Act: -0.1700
Data Index: 3701693 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.1107. Min Act: -0.1700
Data Index: 2516265 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.0794. Min Act: -0.1700
Data Index: 2740593 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.1107. Min Act: -0.1700
Data Index: 8830538 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.0794. Min Act: -0.1700
Data Index: 1034520 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.0794. Min Act: -0.1700
Data Index: 6681572 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.0482. Min Act: -0.1700
Data Index: 268306 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4857. Min Range: -5.4857
Max Act: 5.0482. Min Act: -0.1700
Data Index: 2248820 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19