Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6253 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.8194. Min Act: -0.1700
Data Index: 3959379 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.7257. Min Act: -0.1700
Data Index: 3962964 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6944. Min Act: -0.1700
Data Index: 2298035 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6632. Min Act: -0.1700
Data Index: 186422 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6632. Min Act: -0.1700
Data Index: 3988790 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5694. Min Act: -0.1700
Data Index: 5793145 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5694. Min Act: -0.1700
Data Index: 2740931 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5382. Min Act: -0.1700
Data Index: 1074325 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5382. Min Act: -0.1700
Data Index: 8379812 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5382. Min Act: -0.1700
Data Index: 6447363 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5069. Min Act: -0.1700
Data Index: 2689385 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4757. Min Act: -0.1700
Data Index: 2003912 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4757. Min Act: -0.1700
Data Index: 6496917 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4444. Min Act: -0.1700
Data Index: 7196536 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4444. Min Act: -0.1700
Data Index: 4924235 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4444. Min Act: -0.1700
Data Index: 8354683 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4444. Min Act: -0.1700
Data Index: 2003917 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4757. Min Act: -0.1700
Data Index: 1363267 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4444. Min Act: -0.1700
Data Index: 5389466 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.4444. Min Act: -0.1700
Data Index: 1781380 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19