Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5631 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.9764. Min Act: -0.1700
Data Index: 1004051 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0077. Min Range: -7.0077
Max Act: 7.0077. Min Act: -0.1700
Data Index: 4144573 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.8514. Min Act: -0.1700
Data Index: 3240709 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.9139. Min Act: -0.1700
Data Index: 2005767 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.7264. Min Act: -0.1700
Data Index: 8208477 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.6952. Min Act: -0.1700
Data Index: 1101358 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.6952. Min Act: -0.1700
Data Index: 8775605 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.6014. Min Act: -0.1700
Data Index: 119558 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.6014. Min Act: -0.1700
Data Index: 8526834 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.5389. Min Act: -0.1700
Data Index: 3928316 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.4452. Min Act: -0.1700
Data Index: 7444303 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.4452. Min Act: -0.1700
Data Index: 4295258 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.4139. Min Act: -0.1700
Data Index: 1673547 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.4139. Min Act: -0.1700
Data Index: 3796340 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.4452. Min Act: -0.1700
Data Index: 6566404 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.3827. Min Act: -0.1700
Data Index: 6206815 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.3514. Min Act: -0.1700
Data Index: 4914335 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.3202. Min Act: -0.1700
Data Index: 6283505 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.3202. Min Act: -0.1700
Data Index: 8333256 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0077. Min Range: -7.0077
Max Act: 6.3202. Min Act: -0.1700
Data Index: 7726872 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19