Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.3893. Min Act: -0.1700
Data Index: 3420702 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.2955. Min Act: -0.1700
Data Index: 826723 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.2643. Min Act: -0.1700
Data Index: 4192861 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.2330. Min Act: -0.1700
Data Index: 8501879 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.2017. Min Act: -0.1700
Data Index: 4976238 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.1392. Min Act: -0.1700
Data Index: 8175721 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.1392. Min Act: -0.1700
Data Index: 1941149 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.1080. Min Act: -0.1700
Data Index: 5759471 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.1080. Min Act: -0.1700
Data Index: 1787214 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.1080. Min Act: -0.1700
Data Index: 80383 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0767. Min Act: -0.1700
Data Index: 7257339 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0455. Min Act: -0.1700
Data Index: 8479913 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0767. Min Act: -0.1700
Data Index: 4520600 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0767. Min Act: -0.1700
Data Index: 3489301 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0767. Min Act: -0.1700
Data Index: 5972588 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0455. Min Act: -0.1700
Data Index: 4059745 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0767. Min Act: -0.1700
Data Index: 2123852 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0455. Min Act: -0.1700
Data Index: 5604335 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0455. Min Act: -0.1700
Data Index: 3656041 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3893. Min Range: -4.3893
Max Act: 4.0455. Min Act: -0.1700
Data Index: 7079158 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19