Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6734. Min Range: -7.6734
Max Act: 7.6734. Min Act: -0.1700
Data Index: 5788538 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6734. Min Range: -7.6734
Max Act: 7.2359. Min Act: -0.1700
Data Index: 2013892 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6734. Min Range: -7.6734
Max Act: 7.2047. Min Act: -0.1700
Data Index: 6961434 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6734. Min Range: -7.6734
Max Act: 7.1734. Min Act: -0.1700
Data Index: 4914219 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6734. Min Range: -7.6734
Max Act: 7.1109. Min Act: -0.1700
Data Index: 8749888 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6734. Min Range: -7.6734
Max Act: 7.0797. Min Act: -0.1700
Data Index: 5008684 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.9859. Min Act: -0.1700
Data Index: 3159623 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.9547. Min Act: -0.1700
Data Index: 8734817 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.9859. Min Act: -0.1700
Data Index: 8734815 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.9859. Min Act: -0.1700
Data Index: 4053787 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.9234. Min Act: -0.1700
Data Index: 6625757 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.9234. Min Act: -0.1700
Data Index: 4332991 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.8922. Min Act: -0.1700
Data Index: 1814251 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.8609. Min Act: -0.1700
Data Index: 8298567 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.8609. Min Act: -0.1700
Data Index: 6082712 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.8297. Min Act: -0.1700
Data Index: 7409169 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.8297. Min Act: -0.1700
Data Index: 8695648 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.8297. Min Act: -0.1700
Data Index: 280725 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.7984. Min Act: -0.1700
Data Index: 1594555 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6734. Min Range: -7.6734
Max Act: 6.7984. Min Act: -0.1700
Data Index: 1877589 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19