Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5642. Min Range: -8.5642
Max Act: 8.5642. Min Act: -0.1700
Data Index: 3599597 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5642. Min Range: -8.5642
Max Act: 8.1892. Min Act: -0.1700
Data Index: 2927312 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5642. Min Range: -8.5642
Max Act: 8.1267. Min Act: -0.1700
Data Index: 84670 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5642. Min Range: -8.5642
Max Act: 8.0017. Min Act: -0.1700
Data Index: 7106685 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5642. Min Range: -8.5642
Max Act: 8.0017. Min Act: -0.1700
Data Index: 7388383 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5642. Min Range: -8.5642
Max Act: 8.0017. Min Act: -0.1700
Data Index: 7310293 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.8455. Min Act: -0.1700
Data Index: 1075042 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.8142. Min Act: -0.1700
Data Index: 1514433 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.8142. Min Act: -0.1700
Data Index: 6822569 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.6892. Min Act: -0.1700
Data Index: 8571337 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.6892. Min Act: -0.1700
Data Index: 492993 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.7205. Min Act: -0.1700
Data Index: 3898372 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.6580. Min Act: -0.1700
Data Index: 7945596 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.6580. Min Act: -0.1700
Data Index: 5978725 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.6267. Min Act: -0.1700
Data Index: 1818573 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.5642. Min Act: -0.1700
Data Index: 5518613 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.5642. Min Act: -0.1700
Data Index: 5813266 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.5642. Min Act: -0.1700
Data Index: 7840825 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.5330. Min Act: -0.1700
Data Index: 7310641 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5642. Min Range: -8.5642
Max Act: 7.5330. Min Act: -0.1700
Data Index: 4133635 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19