Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.8330. Min Act: -0.1700
Data Index: 1143552 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.6767. Min Act: -0.1700
Data Index: 795050 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.5517. Min Act: -0.1700
Data Index: 5833677 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.5830. Min Act: -0.1700
Data Index: 3148657 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.4892. Min Act: -0.1700
Data Index: 2341327 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.4892. Min Act: -0.1700
Data Index: 5898342 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.4892. Min Act: -0.1700
Data Index: 4835659 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.4892. Min Act: -0.1700
Data Index: 795053 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3642. Min Act: -0.1700
Data Index: 3053516 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3642. Min Act: -0.1700
Data Index: 7969214 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3642. Min Act: -0.1700
Data Index: 599522 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3017. Min Act: -0.1700
Data Index: 6153669 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3017. Min Act: -0.1700
Data Index: 702381 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3017. Min Act: -0.1700
Data Index: 7348562 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3017. Min Act: -0.1700
Data Index: 8156517 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.2705. Min Act: -0.1700
Data Index: 4928363 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.2392. Min Act: -0.1700
Data Index: 5841845 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.2705. Min Act: -0.1700
Data Index: 3157604 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.3017. Min Act: -0.1700
Data Index: 3469165 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8330. Min Range: -6.8330
Max Act: 6.2392. Min Act: -0.1700
Data Index: 4700706 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19