Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1501 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1988. Min Range: -4.1988
Max Act: 4.1988. Min Act: -0.1700
Data Index: 6436886 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1988. Min Range: -4.1988
Max Act: 4.1363. Min Act: -0.1700
Data Index: 6292652 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1988. Min Range: -4.1988
Max Act: 4.1675. Min Act: -0.1700
Data Index: 7208637 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1988. Min Range: -4.1988
Max Act: 4.0738. Min Act: -0.1700
Data Index: 4976337 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1988. Min Range: -4.1988
Max Act: 4.0738. Min Act: -0.1700
Data Index: 178936 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9800. Min Act: -0.1700
Data Index: 6980615 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9175. Min Act: -0.1700
Data Index: 4167368 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1988. Min Range: -4.1988
Max Act: 4.0425. Min Act: -0.1700
Data Index: 8168256 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9800. Min Act: -0.1700
Data Index: 6517608 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9487. Min Act: -0.1700
Data Index: 7495522 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9175. Min Act: -0.1700
Data Index: 280039 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.7611. Min Act: -0.1700
Data Index: 50190 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.8237. Min Act: -0.1700
Data Index: 5211681 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9487. Min Act: -0.1700
Data Index: 1822819 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9175. Min Act: -0.1700
Data Index: 258453 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.8862. Min Act: -0.1700
Data Index: 2295050 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.8549. Min Act: -0.1700
Data Index: 5348340 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.9487. Min Act: -0.1700
Data Index: 758848 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.8549. Min Act: -0.1700
Data Index: 4451823 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1988. Min Range: -4.1988
Max Act: 3.8862. Min Act: -0.1700
Data Index: 1026565 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19