Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1818. Min Range: -9.1818
Max Act: 9.1818. Min Act: -0.1700
Data Index: 785979 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.8068. Min Act: -0.1700
Data Index: 6591836 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.8693. Min Act: -0.1700
Data Index: 80314 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.8068. Min Act: -0.1700
Data Index: 6045184 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.6193. Min Act: -0.1700
Data Index: 3669477 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.6818. Min Act: -0.1700
Data Index: 343210 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.6193. Min Act: -0.1700
Data Index: 3575029 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.6193. Min Act: -0.1700
Data Index: 757695 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.5568. Min Act: -0.1700
Data Index: 7480123 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.6193. Min Act: -0.1699
Data Index: 7085889 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.4318. Min Act: -0.1700
Data Index: 1393969 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.4943. Min Act: -0.1700
Data Index: 2768008 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.4318. Min Act: -0.1700
Data Index: 1559903 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.4943. Min Act: -0.1700
Data Index: 4373209 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.3693. Min Act: -0.1700
Data Index: 5688096 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.4318. Min Act: -0.1700
Data Index: 6555462 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.4943. Min Act: -0.1700
Data Index: 688865 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.3693. Min Act: -0.1700
Data Index: 7721818 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.3693. Min Act: -0.1700
Data Index: 8190620 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1818. Min Range: -9.1818
Max Act: 8.3693. Min Act: -0.1700
Data Index: 5876992 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19