Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 918 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.9788. Min Act: -0.1700
Data Index: 4111693 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.8538. Min Act: -0.1700
Data Index: 6483003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.8538. Min Act: -0.1700
Data Index: 7717798 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7912. Min Act: -0.1700
Data Index: 7527838 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7756. Min Act: -0.1700
Data Index: 6151762 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7287. Min Act: -0.1700
Data Index: 8770151 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7599. Min Act: -0.1700
Data Index: 4694908 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7287. Min Act: -0.1700
Data Index: 5827545 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7287. Min Act: -0.1700
Data Index: 387105 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7287. Min Act: -0.1700
Data Index: 2375109 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6974. Min Act: -0.1700
Data Index: 2787514 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.7130. Min Act: -0.1700
Data Index: 6666204 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6974. Min Act: -0.1700
Data Index: 3538048 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6661. Min Act: -0.1700
Data Index: 3480014 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6661. Min Act: -0.1700
Data Index: 8633036 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6817. Min Act: -0.1700
Data Index: 2712392 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6504. Min Act: -0.1700
Data Index: 8653375 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6661. Min Act: -0.1700
Data Index: 3430518 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6661. Min Act: -0.1700
Data Index: 382525 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9788. Min Range: -3.9788
Max Act: 3.6817. Min Act: -0.1700
Data Index: 2995996 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19