Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7022. Min Range: -8.7022
Max Act: 8.7022. Min Act: -0.1700
Data Index: 2110276 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.8585. Min Act: -0.1700
Data Index: 6261855 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.8585. Min Act: -0.1700
Data Index: 2690575 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.8272. Min Act: -0.1700
Data Index: 5517135 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.5460. Min Act: -0.1700
Data Index: 2859295 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.5460. Min Act: -0.1700
Data Index: 4566621 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.4522. Min Act: -0.1700
Data Index: 7056058 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.4522. Min Act: -0.1700
Data Index: 5359898 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.4522. Min Act: -0.1700
Data Index: 2613902 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.3897. Min Act: -0.1700
Data Index: 2896966 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2960. Min Act: -0.1700
Data Index: 8524508 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2960. Min Act: -0.1700
Data Index: 8214407 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2960. Min Act: -0.1700
Data Index: 8233212 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2647. Min Act: -0.1700
Data Index: 6208229 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2647. Min Act: -0.1700
Data Index: 3413424 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2647. Min Act: -0.1700
Data Index: 4916077 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2335. Min Act: -0.1700
Data Index: 7991746 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2335. Min Act: -0.1700
Data Index: 6702157 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.1710. Min Act: -0.1700
Data Index: 8677050 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7022. Min Range: -8.7022
Max Act: 7.2022. Min Act: -0.1700
Data Index: 2761879 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19