Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0084. Min Range: -3.0084
Max Act: 3.0084. Min Act: -0.1700
Data Index: 575991 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8976. Min Act: -0.1700
Data Index: 542409 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8499. Min Act: -0.1700
Data Index: 3453613 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8340. Min Act: -0.1700
Data Index: 4278791 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8340. Min Act: -0.1700
Data Index: 5033058 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8181. Min Act: -0.1700
Data Index: 1841152 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8340. Min Act: -0.1700
Data Index: 1614722 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8340. Min Act: -0.1700
Data Index: 1397292 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8181. Min Act: -0.1700
Data Index: 4917263 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8181. Min Act: -0.1700
Data Index: 5288883 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8181. Min Act: -0.1700
Data Index: 1756763 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8022. Min Act: -0.1700
Data Index: 7734906 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8022. Min Act: -0.1700
Data Index: 940107 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8181. Min Act: -0.1700
Data Index: 6416487 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.7863. Min Act: -0.1700
Data Index: 2382268 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8022. Min Act: -0.1700
Data Index: 1041244 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8022. Min Act: -0.1700
Data Index: 3694504 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8022. Min Act: -0.1700
Data Index: 2053088 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8022. Min Act: -0.1700
Data Index: 3191620 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0084. Min Range: -3.0084
Max Act: 2.8022. Min Act: -0.1700
Data Index: 5966735 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19