Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4960 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.3400. Min Act: -0.1700
Data Index: 2656496 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.3088. Min Act: -0.1700
Data Index: 2434329 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.2463. Min Act: -0.1700
Data Index: 6421036 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.2150. Min Act: -0.1700
Data Index: 2543731 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1838. Min Act: -0.1700
Data Index: 3117074 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.2150. Min Act: -0.1700
Data Index: 6762214 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1838. Min Act: -0.1700
Data Index: 1544715 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1838. Min Act: -0.1700
Data Index: 2940410 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1838. Min Act: -0.1700
Data Index: 6387462 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1525. Min Act: -0.1700
Data Index: 4535590 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1213. Min Act: -0.1700
Data Index: 5036369 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1213. Min Act: -0.1700
Data Index: 7509658 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.1213. Min Act: -0.1700
Data Index: 1837294 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.0588. Min Act: -0.1700
Data Index: 5590758 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.0900. Min Act: -0.1700
Data Index: 844398 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.0588. Min Act: -0.1700
Data Index: 7485245 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.0588. Min Act: -0.1700
Data Index: 7346546 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.0588. Min Act: -0.1700
Data Index: 3875624 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.0275. Min Act: -0.1700
Data Index: 5283935 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3400. Min Range: -6.3400
Max Act: 6.0588. Min Act: -0.1700
Data Index: 7528593 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19