Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1219. Min Range: -8.1219
Max Act: 8.1219. Min Act: -0.1700
Data Index: 7665341 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.8719. Min Act: -0.1700
Data Index: 3462872 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.5906. Min Act: -0.1700
Data Index: 228034 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.5906. Min Act: -0.1700
Data Index: 568876 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.5906. Min Act: -0.1700
Data Index: 6335437 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.5906. Min Act: -0.1700
Data Index: 7522145 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.5906. Min Act: -0.1700
Data Index: 4153761 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.5594. Min Act: -0.1700
Data Index: 7554689 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.4656. Min Act: -0.1700
Data Index: 1572936 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.4656. Min Act: -0.1700
Data Index: 4084221 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.4031. Min Act: -0.1700
Data Index: 6549702 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.3719. Min Act: -0.1700
Data Index: 6335438 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.4031. Min Act: -0.1700
Data Index: 4779846 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.3719. Min Act: -0.1700
Data Index: 4870755 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.3406. Min Act: -0.1700
Data Index: 2330898 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.2781. Min Act: -0.1700
Data Index: 7175371 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.3094. Min Act: -0.1700
Data Index: 7200836 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.3094. Min Act: -0.1700
Data Index: 4279048 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.2781. Min Act: -0.1700
Data Index: 2671441 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1219. Min Range: -8.1219
Max Act: 7.2469. Min Act: -0.1700
Data Index: 7602095 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19