Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4781 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2988. Min Act: -0.1700
Data Index: 477973 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2360. Min Act: -0.1700
Data Index: 3073876 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1888. Min Act: -0.1700
Data Index: 1508350 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1573. Min Act: -0.1700
Data Index: 4636109 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1573. Min Act: -0.1700
Data Index: 7331069 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1258. Min Act: -0.1700
Data Index: 4594018 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1101. Min Act: -0.1700
Data Index: 2561811 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0943. Min Act: -0.1700
Data Index: 4524403 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0943. Min Act: -0.1700
Data Index: 6701812 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0786. Min Act: -0.1700
Data Index: 1038242 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0628. Min Act: -0.1700
Data Index: 2942409 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0786. Min Act: -0.1700
Data Index: 3962623 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0628. Min Act: -0.1700
Data Index: 7044355 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0786. Min Act: -0.1700
Data Index: 2982344 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0628. Min Act: -0.1700
Data Index: 3139913 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0628. Min Act: -0.1700
Data Index: 8347947 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0786. Min Act: -0.1700
Data Index: 352188 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0470. Min Act: -0.1700
Data Index: 4822767 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0470. Min Act: -0.1700
Data Index: 6722468 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0470. Min Act: -0.1700
Data Index: 6200321 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19