Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.5567. Min Act: -0.1700
Data Index: 7197717 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.6192. Min Act: -0.1700
Data Index: 781940 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.5567. Min Act: -0.1700
Data Index: 8308119 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.4317. Min Act: -0.1700
Data Index: 4669065 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.4317. Min Act: -0.1700
Data Index: 975922 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3067. Min Act: -0.1700
Data Index: 2078855 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3692. Min Act: -0.1700
Data Index: 7864017 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3692. Min Act: -0.1700
Data Index: 1570352 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.4317. Min Act: -0.1700
Data Index: 605436 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3067. Min Act: -0.1700
Data Index: 5710015 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3067. Min Act: -0.1700
Data Index: 7517564 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3067. Min Act: -0.1700
Data Index: 8029175 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3067. Min Act: -0.1700
Data Index: 5428166 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.2442. Min Act: -0.1700
Data Index: 7707247 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.3067. Min Act: -0.1700
Data Index: 595481 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.2442. Min Act: -0.1700
Data Index: 6987264 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.2442. Min Act: -0.1700
Data Index: 6570303 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.2442. Min Act: -0.1700
Data Index: 389103 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.2442. Min Act: -0.1700
Data Index: 6829463 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6192. Min Range: -11.6192
Max Act: 11.2442. Min Act: -0.1700
Data Index: 2345985 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19