Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4606 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.4130. Min Act: -0.1700
Data Index: 774994 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.2880. Min Act: -0.1700
Data Index: 1085711 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.1943. Min Act: -0.1700
Data Index: 6559901 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.2255. Min Act: -0.1700
Data Index: 4762852 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.2255. Min Act: -0.1700
Data Index: 6529609 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.1317. Min Act: -0.1700
Data Index: 2786113 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.1005. Min Act: -0.1700
Data Index: 321457 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.1005. Min Act: -0.1700
Data Index: 6419615 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.1005. Min Act: -0.1700
Data Index: 8669785 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0380. Min Act: -0.1700
Data Index: 2505270 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0380. Min Act: -0.1700
Data Index: 4688957 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0067. Min Act: -0.1700
Data Index: 6438667 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0692. Min Act: -0.1700
Data Index: 3979266 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0380. Min Act: -0.1700
Data Index: 1946572 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0380. Min Act: -0.1700
Data Index: 6018363 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0380. Min Act: -0.1700
Data Index: 7366736 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0067. Min Act: -0.1700
Data Index: 1303157 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4130. Min Range: -4.4130
Max Act: 4.0067. Min Act: -0.1700
Data Index: 6922508 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4130. Min Range: -4.4130
Max Act: 3.9755. Min Act: -0.1700
Data Index: 1565638 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4130. Min Range: -4.4130
Max Act: 3.9755. Min Act: -0.1700
Data Index: 505742 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19