Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.9041. Min Act: -0.1700
Data Index: 3294179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.8728. Min Act: -0.1700
Data Index: 6041090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.8416. Min Act: -0.1700
Data Index: 8194863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.8103. Min Act: -0.1700
Data Index: 5704699 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.8103. Min Act: -0.1700
Data Index: 1871188 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.8103. Min Act: -0.1700
Data Index: 3639963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 5865606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 5694623 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 1242674 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 2306753 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 7776911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 7028224 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 6368200 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 6240162 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 1821358 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7791. Min Act: -0.1700
Data Index: 2854264 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7478. Min Act: -0.1700
Data Index: 2303579 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7478. Min Act: -0.1700
Data Index: 3734539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7478. Min Act: -0.1700
Data Index: 3748246 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9041. Min Range: -4.9041
Max Act: 4.7478. Min Act: -0.1700
Data Index: 5447866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19