Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0225. Min Range: -8.0225
Max Act: 8.0225. Min Act: -0.1700
Data Index: 4635128 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.9600. Min Act: -0.1700
Data Index: 7445378 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.8975. Min Act: -0.1700
Data Index: 7796300 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.8350. Min Act: -0.1700
Data Index: 4570338 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.7100. Min Act: -0.1700
Data Index: 961989 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.6788. Min Act: -0.1700
Data Index: 6017754 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.6475. Min Act: -0.1700
Data Index: 1484571 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.6788. Min Act: -0.1700
Data Index: 3219705 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.6475. Min Act: -0.1700
Data Index: 7438217 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.6163. Min Act: -0.1700
Data Index: 195991 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.6163. Min Act: -0.1700
Data Index: 8090717 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.6163. Min Act: -0.1700
Data Index: 754683 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.5850. Min Act: -0.1700
Data Index: 214184 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.5538. Min Act: -0.1700
Data Index: 6451807 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.5225. Min Act: -0.1700
Data Index: 7804777 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.4913. Min Act: -0.1700
Data Index: 560084 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.3350. Min Act: -0.1700
Data Index: 260381 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.2725. Min Act: -0.1700
Data Index: 5419021 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.2725. Min Act: -0.1700
Data Index: 6268609 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0225. Min Range: -8.0225
Max Act: 7.2100. Min Act: -0.1700
Data Index: 7570788 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19