Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1137 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4456. Min Range: -6.4456
Max Act: 6.4456. Min Act: -0.1700
Data Index: 8660057 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4456. Min Range: -6.4456
Max Act: 6.1643. Min Act: -0.1700
Data Index: 6612970 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4456. Min Range: -6.4456
Max Act: 6.0393. Min Act: -0.1700
Data Index: 5568641 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4456. Min Range: -6.4456
Max Act: 6.0081. Min Act: -0.1700
Data Index: 4768009 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.9768. Min Act: -0.1700
Data Index: 2528371 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.9456. Min Act: -0.1700
Data Index: 7187083 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.9768. Min Act: -0.1700
Data Index: 2502154 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4456. Min Range: -6.4456
Max Act: 6.0081. Min Act: -0.1700
Data Index: 5935908 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4456. Min Range: -6.4456
Max Act: 6.0081. Min Act: -0.1700
Data Index: 4747860 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.9456. Min Act: -0.1700
Data Index: 347500 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.9768. Min Act: -0.1700
Data Index: 7315024 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.9143. Min Act: -0.1700
Data Index: 6889502 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.8518. Min Act: -0.1700
Data Index: 4936422 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.8831. Min Act: -0.1700
Data Index: 7391359 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.8206. Min Act: -0.1700
Data Index: 7334508 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.8518. Min Act: -0.1700
Data Index: 564957 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.7893. Min Act: -0.1700
Data Index: 6720372 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.8206. Min Act: -0.1700
Data Index: 8126411 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.7893. Min Act: -0.1700
Data Index: 6305568 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4456. Min Range: -6.4456
Max Act: 5.7581. Min Act: -0.1700
Data Index: 6189360 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19