Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4173 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5229. Min Range: -8.5229
Max Act: 8.5229. Min Act: -0.1700
Data Index: 1503701 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5229. Min Range: -8.5229
Max Act: 8.2104. Min Act: -0.1700
Data Index: 8063278 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5229. Min Range: -8.5229
Max Act: 8.0854. Min Act: -0.1700
Data Index: 5285357 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5229. Min Range: -8.5229
Max Act: 8.0854. Min Act: -0.1700
Data Index: 5285359 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5229. Min Range: -8.5229
Max Act: 8.0229. Min Act: -0.1700
Data Index: 1265513 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.8979. Min Act: -0.1700
Data Index: 5984493 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.8354. Min Act: -0.1700
Data Index: 6830919 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.8042. Min Act: -0.1700
Data Index: 2680270 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.7104. Min Act: -0.1700
Data Index: 428798 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6792. Min Act: -0.1700
Data Index: 4776590 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6792. Min Act: -0.1700
Data Index: 1048199 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6792. Min Act: -0.1700
Data Index: 2726585 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6792. Min Act: -0.1700
Data Index: 5242553 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6479. Min Act: -0.1700
Data Index: 650438 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.5854. Min Act: -0.1700
Data Index: 1523812 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6167. Min Act: -0.1700
Data Index: 3401130 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6167. Min Act: -0.1700
Data Index: 8394970 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6479. Min Act: -0.1700
Data Index: 8023803 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.6167. Min Act: -0.1700
Data Index: 4430157 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5229. Min Range: -8.5229
Max Act: 7.5542. Min Act: -0.1700
Data Index: 7796237 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19