Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 245 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.4948. Min Act: -0.1700
Data Index: 661597 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.2760. Min Act: -0.1700
Data Index: 1082503 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.1198. Min Act: -0.1700
Data Index: 8513352 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.1198. Min Act: -0.1700
Data Index: 5355029 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.0260. Min Act: -0.1700
Data Index: 2901986 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.9948. Min Act: -0.1700
Data Index: 8119525 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.9635. Min Act: -0.1700
Data Index: 1649303 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.9323. Min Act: -0.1700
Data Index: 149387 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.9010. Min Act: -0.1700
Data Index: 6383375 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.9010. Min Act: -0.1700
Data Index: 1138429 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3099757 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8698. Min Act: -0.1700
Data Index: 1733918 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8698. Min Act: -0.1700
Data Index: 5703768 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8385. Min Act: -0.1700
Data Index: 6313055 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8073. Min Act: -0.1700
Data Index: 1106128 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8073. Min Act: -0.1700
Data Index: 339382 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8073. Min Act: -0.1700
Data Index: 7032804 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8073. Min Act: -0.1700
Data Index: 7165483 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.8073. Min Act: -0.1700
Data Index: 4993776 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4948. Min Range: -7.4948
Max Act: 6.7760. Min Act: -0.1700
Data Index: 2903830 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19