Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.5634. Min Act: -0.1700
Data Index: 7844559 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.5634. Min Act: -0.1700
Data Index: 3279493 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.5009. Min Act: -0.1700
Data Index: 2294001 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.5009. Min Act: -0.1700
Data Index: 3064083 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.4697. Min Act: -0.1700
Data Index: 6078182 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.4072. Min Act: -0.1700
Data Index: 6821192 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.4072. Min Act: -0.1700
Data Index: 174300 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.4072. Min Act: -0.1700
Data Index: 1393317 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.2509. Min Act: -0.1700
Data Index: 5192169 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.2509. Min Act: -0.1700
Data Index: 1151401 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.2197. Min Act: -0.1700
Data Index: 8668760 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.1884. Min Act: -0.1700
Data Index: 1190347 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.1884. Min Act: -0.1700
Data Index: 8412741 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.1572. Min Act: -0.1700
Data Index: 5746748 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.1572. Min Act: -0.1700
Data Index: 8410789 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.1572. Min Act: -0.1700
Data Index: 6244447 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.1259. Min Act: -0.1700
Data Index: 7892395 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.1259. Min Act: -0.1700
Data Index: 2830327 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.0946. Min Act: -0.1700
Data Index: 350608 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5634. Min Range: -4.5634
Max Act: 4.0946. Min Act: -0.1700
Data Index: 6851240 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19