Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.8973. Min Act: -0.1700
Data Index: 3401749 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.3973. Min Act: -0.1700
Data Index: 7782853 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.3973. Min Act: -0.1700
Data Index: 329697 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.2098. Min Act: -0.1700
Data Index: 3570210 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.0848. Min Act: -0.1700
Data Index: 2363205 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.1473. Min Act: -0.1700
Data Index: 6289101 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.0848. Min Act: -0.1700
Data Index: 7198341 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 7646053 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.0223. Min Act: -0.1700
Data Index: 4814540 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.0223. Min Act: -0.1700
Data Index: 2966443 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.0223. Min Act: -0.1700
Data Index: 7758594 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8973. Min Range: -9.8973
Max Act: 9.0848. Min Act: -0.1700
Data Index: 8713799 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 2372447 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 2673891 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 7481880 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 1649035 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 6020389 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 1673578 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 450339 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8973. Min Range: -9.8973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 2366734 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19