Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.6946. Min Act: -0.1700
Data Index: 820272 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.6634. Min Act: -0.1700
Data Index: 99507 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.6009. Min Act: -0.1700
Data Index: 4093300 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3821. Min Act: -0.1700
Data Index: 879156 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3821. Min Act: -0.1700
Data Index: 2538106 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3821. Min Act: -0.1700
Data Index: 2900400 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3196. Min Act: -0.1700
Data Index: 507606 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3509. Min Act: -0.1700
Data Index: 4012912 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3509. Min Act: -0.1700
Data Index: 1969152 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3509. Min Act: -0.1700
Data Index: 7342832 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2571. Min Act: -0.1700
Data Index: 8174916 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 6668770 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 6152942 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 845478 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 7486 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 3865053 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 4360511 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 7130619 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2571. Min Act: -0.1700
Data Index: 6101809 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2571. Min Act: -0.1700
Data Index: 1452772 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19