Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2511 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.6971. Min Act: -0.1700
Data Index: 5541568 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.6814. Min Act: -0.1700
Data Index: 3786126 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.6345. Min Act: -0.1700
Data Index: 6058025 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.6345. Min Act: -0.1700
Data Index: 2086547 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.6032. Min Act: -0.1700
Data Index: 5898229 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.6032. Min Act: -0.1700
Data Index: 5253770 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5719. Min Act: -0.1700
Data Index: 976849 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5406. Min Act: -0.1700
Data Index: 6941407 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5249. Min Act: -0.1700
Data Index: 3134542 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5719. Min Act: -0.1700
Data Index: 176440 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5249. Min Act: -0.1700
Data Index: 6941406 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5249. Min Act: -0.1700
Data Index: 1198829 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4936. Min Act: -0.1700
Data Index: 5480445 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5093. Min Act: -0.1700
Data Index: 2688426 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4936. Min Act: -0.1700
Data Index: 8340590 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4936. Min Act: -0.1700
Data Index: 4042158 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5093. Min Act: -0.1700
Data Index: 5241161 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4936. Min Act: -0.1700
Data Index: 242695 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4936. Min Act: -0.1700
Data Index: 6277413 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4779. Min Act: -0.1700
Data Index: 1736202 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19