Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.5345. Min Act: -0.1700
Data Index: 422943 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.5345. Min Act: -0.1700
Data Index: 4311122 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.5031. Min Act: -0.1700
Data Index: 4213832 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.4718. Min Act: -0.1700
Data Index: 6629675 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.4718. Min Act: -0.1700
Data Index: 5247827 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.4561. Min Act: -0.1700
Data Index: 3018964 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.4091. Min Act: -0.1700
Data Index: 5357860 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3934. Min Act: -0.1700
Data Index: 3581944 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3934. Min Act: -0.1700
Data Index: 7226976 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3778. Min Act: -0.1700
Data Index: 5820135 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3778. Min Act: -0.1700
Data Index: 8616874 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3778. Min Act: -0.1700
Data Index: 1730716 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3464. Min Act: -0.1700
Data Index: 2005890 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3464. Min Act: -0.1700
Data Index: 1207975 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3307. Min Act: -0.1700
Data Index: 2379788 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3307. Min Act: -0.1700
Data Index: 3433793 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3307. Min Act: -0.1700
Data Index: 8516787 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3307. Min Act: -0.1700
Data Index: 2176641 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.3150. Min Act: -0.1700
Data Index: 7068359 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5345. Min Range: -3.5345
Max Act: 3.2993. Min Act: -0.1700
Data Index: 5695466 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19