Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4145 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.5536. Min Act: -0.1700
Data Index: 2610491 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.4599. Min Act: -0.1700
Data Index: 7714442 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3661. Min Act: -0.1700
Data Index: 5495159 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3661. Min Act: -0.1700
Data Index: 3882731 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3349. Min Act: -0.1700
Data Index: 5586516 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3661. Min Act: -0.1700
Data Index: 349138 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3349. Min Act: -0.1700
Data Index: 89844 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3036. Min Act: -0.1700
Data Index: 1569886 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3349. Min Act: -0.1700
Data Index: 4866240 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.3036. Min Act: -0.1700
Data Index: 6713475 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.2724. Min Act: -0.1700
Data Index: 2592242 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.2724. Min Act: -0.1700
Data Index: 791542 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.2724. Min Act: -0.1700
Data Index: 6097572 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.2411. Min Act: -0.1700
Data Index: 4395658 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.2099. Min Act: -0.1700
Data Index: 8153380 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.2099. Min Act: -0.1700
Data Index: 3904924 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.2099. Min Act: -0.1700
Data Index: 3034581 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.1786. Min Act: -0.1700
Data Index: 355665 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.1786. Min Act: -0.1700
Data Index: 6683153 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5536. Min Range: -5.5536
Max Act: 5.1786. Min Act: -0.1700
Data Index: 6489069 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19