Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5260 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.8201. Min Act: -0.1700
Data Index: 7196582 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.6443. Min Act: -0.1684
Data Index: 8322640 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.6122. Min Act: -0.1698
Data Index: 4375755 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.5800. Min Act: -0.1700
Data Index: 5344400 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.5315. Min Act: -0.1700
Data Index: 5266422 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4992. Min Act: -0.1685
Data Index: 7002207 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4830. Min Act: -0.1700
Data Index: 4265096 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4667. Min Act: -0.1697
Data Index: 4341697 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4667. Min Act: -0.1700
Data Index: 5829327 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4505. Min Act: -0.1685
Data Index: 2089418 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4505. Min Act: -0.1700
Data Index: 128723 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4342. Min Act: -0.1694
Data Index: 611112 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.4342. Min Act: -0.1696
Data Index: 6780512 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.3690. Min Act: -0.1697
Data Index: 6015670 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.3690. Min Act: -0.1700
Data Index: 7838353 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.3690. Min Act: -0.1618
Data Index: 816813 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.3690. Min Act: -0.1699
Data Index: 4644408 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.3690. Min Act: -0.1699
Data Index: 8650716 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.3526. Min Act: -0.1698
Data Index: 2285846 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8201. Min Range: -2.8201
Max Act: 2.3526. Min Act: -0.1693
Data Index: 7698007 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19