Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3754 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.5982. Min Act: -0.1700
Data Index: 5771377 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.5982. Min Act: -0.1700
Data Index: 3533952 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.5357. Min Act: -0.1700
Data Index: 6541082 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.5044. Min Act: -0.1700
Data Index: 6465610 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.5357. Min Act: -0.1700
Data Index: 6031183 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.4732. Min Act: -0.1700
Data Index: 3974109 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.4107. Min Act: -0.1700
Data Index: 4864943 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3794. Min Act: -0.1700
Data Index: 1983514 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3794. Min Act: -0.1700
Data Index: 8775915 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3794. Min Act: -0.1700
Data Index: 701641 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3794. Min Act: -0.1700
Data Index: 7249875 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3482. Min Act: -0.1700
Data Index: 6925614 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3482. Min Act: -0.1700
Data Index: 6528364 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3482. Min Act: -0.1700
Data Index: 8387455 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.2857. Min Act: -0.1700
Data Index: 3045372 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.3169. Min Act: -0.1700
Data Index: 5441915 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.2544. Min Act: -0.1700
Data Index: 1065533 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.2544. Min Act: -0.1700
Data Index: 4885336 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.2857. Min Act: -0.1700
Data Index: 7172223 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.2857. Min Act: -0.1700
Data Index: 6272170 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19