Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1943 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.9019. Min Act: -0.1700
Data Index: 1380520 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.8081. Min Act: -0.1700
Data Index: 984345 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.8081. Min Act: -0.1700
Data Index: 5512591 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.7456. Min Act: -0.1700
Data Index: 2938143 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.7456. Min Act: -0.1700
Data Index: 2196471 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.7456. Min Act: -0.1700
Data Index: 1503655 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.7144. Min Act: -0.1700
Data Index: 3534557 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6519. Min Act: -0.1700
Data Index: 6783120 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6206. Min Act: -0.1700
Data Index: 7253380 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6206. Min Act: -0.1700
Data Index: 569978 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6206. Min Act: -0.1700
Data Index: 3824145 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6206. Min Act: -0.1700
Data Index: 7432735 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6206. Min Act: -0.1700
Data Index: 7416442 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.5581. Min Act: -0.1700
Data Index: 4786631 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.5894. Min Act: -0.1700
Data Index: 1252878 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6206. Min Act: -0.1700
Data Index: 6783121 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.5894. Min Act: -0.1700
Data Index: 1542195 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.5894. Min Act: -0.1700
Data Index: 5807111 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.5894. Min Act: -0.1700
Data Index: 5157601 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6206. Min Act: -0.1700
Data Index: 1976866 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19