Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1830 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0797. Min Range: -4.0797
Max Act: 4.0797. Min Act: -0.1700
Data Index: 5775035 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0797. Min Range: -4.0797
Max Act: 4.0485. Min Act: -0.1700
Data Index: 6842530 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.9860. Min Act: -0.1700
Data Index: 8092573 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.9547. Min Act: -0.1700
Data Index: 2144634 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.9547. Min Act: -0.1700
Data Index: 6842534 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8922. Min Act: -0.1700
Data Index: 2499444 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.9234. Min Act: -0.1700
Data Index: 932248 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8922. Min Act: -0.1700
Data Index: 101127 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.9234. Min Act: -0.1700
Data Index: 2496813 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8609. Min Act: -0.1700
Data Index: 2359608 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8922. Min Act: -0.1700
Data Index: 2595705 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8922. Min Act: -0.1700
Data Index: 1324414 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8609. Min Act: -0.1700
Data Index: 6210056 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8922. Min Act: -0.1700
Data Index: 4437715 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8296. Min Act: -0.1700
Data Index: 5766136 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8609. Min Act: -0.1700
Data Index: 2004438 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8296. Min Act: -0.1700
Data Index: 1558341 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8296. Min Act: -0.1700
Data Index: 6827203 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.8296. Min Act: -0.1700
Data Index: 4562188 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0797. Min Range: -4.0797
Max Act: 3.7984. Min Act: -0.1700
Data Index: 1880745 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19