Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4205 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.7904. Min Act: -0.1700
Data Index: 76385 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.6654. Min Act: -0.1700
Data Index: 2921407 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.6654. Min Act: -0.1700
Data Index: 454747 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.6029. Min Act: -0.1700
Data Index: 8207539 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.6029. Min Act: -0.1700
Data Index: 4748769 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.6029. Min Act: -0.1700
Data Index: 7851884 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.5716. Min Act: -0.1700
Data Index: 2441729 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.5091. Min Act: -0.1700
Data Index: 3128119 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.4466. Min Act: -0.1700
Data Index: 6434983 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.4154. Min Act: -0.1700
Data Index: 6744774 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.4466. Min Act: -0.1700
Data Index: 908939 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.4466. Min Act: -0.1700
Data Index: 1892619 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.4466. Min Act: -0.1700
Data Index: 2310044 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.4154. Min Act: -0.1700
Data Index: 2861803 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.3841. Min Act: -0.1700
Data Index: 1019098 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.3841. Min Act: -0.1700
Data Index: 3963971 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.3841. Min Act: -0.1700
Data Index: 5374198 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.4154. Min Act: -0.1700
Data Index: 5759778 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.3529. Min Act: -0.1700
Data Index: 7101133 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7904. Min Range: -5.7904
Max Act: 5.3529. Min Act: -0.1700
Data Index: 4148647 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19