Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4767 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.9816. Min Act: -0.1700
Data Index: 8714613 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.8878. Min Act: -0.1700
Data Index: 3311811 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.8878. Min Act: -0.1700
Data Index: 7475703 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.8878. Min Act: -0.1700
Data Index: 739743 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.8566. Min Act: -0.1700
Data Index: 842062 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.8566. Min Act: -0.1700
Data Index: 3694554 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7941. Min Act: -0.1700
Data Index: 5227999 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7941. Min Act: -0.1700
Data Index: 6395229 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7628. Min Act: -0.1700
Data Index: 8021835 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7628. Min Act: -0.1700
Data Index: 7268054 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7628. Min Act: -0.1700
Data Index: 7799235 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7316. Min Act: -0.1700
Data Index: 3757379 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7316. Min Act: -0.1700
Data Index: 8404354 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.6691. Min Act: -0.1700
Data Index: 4784902 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7003. Min Act: -0.1700
Data Index: 1465866 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.6691. Min Act: -0.1700
Data Index: 7322418 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7003. Min Act: -0.1700
Data Index: 7805477 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.6691. Min Act: -0.1700
Data Index: 4982804 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7003. Min Act: -0.1700
Data Index: 7489655 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9816. Min Range: -4.9816
Max Act: 4.7003. Min Act: -0.1700
Data Index: 3729943 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19