Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 259 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.1983. Min Act: -0.1700
Data Index: 2128336 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.2140. Min Act: -0.1700
Data Index: 7237380 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.1038. Min Act: -0.1700
Data Index: 976114 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.0565. Min Act: -0.1700
Data Index: 1667275 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.0407. Min Act: -0.1700
Data Index: 3269129 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.0565. Min Act: -0.1700
Data Index: 6852672 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9933. Min Act: -0.1700
Data Index: 5914347 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.0249. Min Act: -0.1700
Data Index: 5225109 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9933. Min Act: -0.1700
Data Index: 1823863 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9617. Min Act: -0.1700
Data Index: 192213 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2140. Min Range: -3.2140
Max Act: 3.0091. Min Act: -0.1700
Data Index: 1128295 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9459. Min Act: -0.1700
Data Index: 6983738 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9300. Min Act: -0.1700
Data Index: 7989884 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9300. Min Act: -0.1700
Data Index: 8142650 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9300. Min Act: -0.1700
Data Index: 3591146 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.8983. Min Act: -0.1700
Data Index: 4849338 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.8983. Min Act: -0.1700
Data Index: 7995892 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.8983. Min Act: -0.1700
Data Index: 8523586 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.9300. Min Act: -0.1700
Data Index: 6179906 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2140. Min Range: -3.2140
Max Act: 2.8983. Min Act: -0.1700
Data Index: 5555690 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19