Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.8222. Min Act: -0.1700
Data Index: 2528471 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.7284. Min Act: -0.1700
Data Index: 1573680 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.6971. Min Act: -0.1700
Data Index: 2346479 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.6658. Min Act: -0.1700
Data Index: 6307752 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.6658. Min Act: -0.1700
Data Index: 7849568 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5876. Min Act: -0.1700
Data Index: 5516972 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5719. Min Act: -0.1700
Data Index: 283098 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5563. Min Act: -0.1700
Data Index: 1472219 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5250. Min Act: -0.1700
Data Index: 5243252 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5250. Min Act: -0.1700
Data Index: 1900174 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5093. Min Act: -0.1700
Data Index: 3327735 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5093. Min Act: -0.1700
Data Index: 5925626 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5250. Min Act: -0.1700
Data Index: 2250997 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5093. Min Act: -0.1700
Data Index: 2630738 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5093. Min Act: -0.1700
Data Index: 6461001 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5093. Min Act: -0.1700
Data Index: 3994185 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.4936. Min Act: -0.1700
Data Index: 1088858 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.5093. Min Act: -0.1700
Data Index: 1386468 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.4780. Min Act: -0.1700
Data Index: 2595520 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8222. Min Range: -3.8222
Max Act: 3.4936. Min Act: -0.1700
Data Index: 7482447 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19