Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.3550. Min Act: -0.1700
Data Index: 8581782 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.3550. Min Act: -0.1700
Data Index: 8012275 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.3550. Min Act: -0.1700
Data Index: 2934910 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.3237. Min Act: -0.1700
Data Index: 6830596 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.3237. Min Act: -0.1700
Data Index: 6316797 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.3237. Min Act: -0.1700
Data Index: 2934911 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.2612. Min Act: -0.1700
Data Index: 2503440 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.2300. Min Act: -0.1700
Data Index: 2340908 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.1987. Min Act: -0.1700
Data Index: 5356883 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.1050. Min Act: -0.1700
Data Index: 1594978 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.1050. Min Act: -0.1700
Data Index: 4617020 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.1050. Min Act: -0.1700
Data Index: 2737814 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.0737. Min Act: -0.1700
Data Index: 3199163 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.1050. Min Act: -0.1700
Data Index: 5551813 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.1050. Min Act: -0.1700
Data Index: 1805830 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.0737. Min Act: -0.1700
Data Index: 5822631 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.0425. Min Act: -0.1700
Data Index: 5350200 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.0112. Min Act: -0.1700
Data Index: 6063649 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.0112. Min Act: -0.1700
Data Index: 6123152 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3550. Min Range: -7.3550
Max Act: 7.0112. Min Act: -0.1700
Data Index: 7742960 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19