Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 353 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0206. Min Range: -5.0206
Max Act: 5.0206. Min Act: -0.1700
Data Index: 6639746 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.9581. Min Act: -0.1700
Data Index: 1962380 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.9269. Min Act: -0.1700
Data Index: 6801727 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.8331. Min Act: -0.1700
Data Index: 512999 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.8331. Min Act: -0.1700
Data Index: 2087013 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.8019. Min Act: -0.1700
Data Index: 8227006 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.8019. Min Act: -0.1700
Data Index: 1600071 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.8019. Min Act: -0.1700
Data Index: 3176697 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.8019. Min Act: -0.1700
Data Index: 5729186 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7706. Min Act: -0.1700
Data Index: 396434 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7706. Min Act: -0.1700
Data Index: 4079508 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7706. Min Act: -0.1700
Data Index: 1325603 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7706. Min Act: -0.1700
Data Index: 6008784 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7706. Min Act: -0.1700
Data Index: 7083822 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3991413 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7394. Min Act: -0.1700
Data Index: 5739780 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7081. Min Act: -0.1700
Data Index: 389901 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.7081. Min Act: -0.1700
Data Index: 8135171 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.6769. Min Act: -0.1700
Data Index: 6619655 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0206. Min Range: -5.0206
Max Act: 4.6769. Min Act: -0.1700
Data Index: 2466855 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19