Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.3560. Min Act: -0.1700
Data Index: 7072787 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2932. Min Act: -0.1700
Data Index: 7072792 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2303. Min Act: -0.1700
Data Index: 1718799 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2146. Min Act: -0.1700
Data Index: 3201931 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2146. Min Act: -0.1700
Data Index: 7288567 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2146. Min Act: -0.1700
Data Index: 182695 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2146. Min Act: -0.1700
Data Index: 4254738 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2146. Min Act: -0.1700
Data Index: 1139981 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1989. Min Act: -0.1700
Data Index: 6387503 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1989. Min Act: -0.1700
Data Index: 2112072 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1989. Min Act: -0.1700
Data Index: 3199252 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1832. Min Act: -0.1700
Data Index: 2920710 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1832. Min Act: -0.1700
Data Index: 7172528 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1674. Min Act: -0.1700
Data Index: 3922 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1674. Min Act: -0.1700
Data Index: 3761951 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1674. Min Act: -0.1700
Data Index: 3684937 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1674. Min Act: -0.1700
Data Index: 5097393 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1674. Min Act: -0.1700
Data Index: 5300417 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1674. Min Act: -0.1700
Data Index: 5868176 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1517. Min Act: -0.1700
Data Index: 2707569 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19