Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0917. Min Act: -0.1700
Data Index: 1592270 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0829. Min Act: -0.1699
Data Index: 2373390 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0742. Min Act: -0.1696
Data Index: 97830 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0654. Min Act: -0.1700
Data Index: 7807313 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0567. Min Act: -0.1699
Data Index: 428667 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0480. Min Act: -0.1699
Data Index: 4895154 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0567. Min Act: -0.1699
Data Index: 8519327 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0305. Min Act: -0.1699
Data Index: 1124809 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0480. Min Act: -0.1700
Data Index: 1542550 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0480. Min Act: -0.1695
Data Index: 5433980 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0393. Min Act: -0.1699
Data Index: 8803032 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0393. Min Act: -0.1698
Data Index: 4027074 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0218. Min Act: -0.1679
Data Index: 6547668 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0305. Min Act: -0.1700
Data Index: 775684 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0393. Min Act: -0.1700
Data Index: 8181027 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0305. Min Act: -0.1699
Data Index: 7546324 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0305. Min Act: -0.1698
Data Index: 3914435 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0305. Min Act: -0.1700
Data Index: 6801623 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0131. Min Act: -0.1699
Data Index: 5051954 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0917. Min Range: -1.0917
Max Act: 1.0131. Min Act: -0.1698
Data Index: 237809 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19