Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.9878. Min Act: -0.1700
Data Index: 3625704 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.8940. Min Act: -0.1700
Data Index: 3383130 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.7065. Min Act: -0.1700
Data Index: 2639621 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.5815. Min Act: -0.1700
Data Index: 2778978 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.5190. Min Act: -0.1699
Data Index: 1843596 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.4565. Min Act: -0.1700
Data Index: 2886036 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.3940. Min Act: -0.1699
Data Index: 3287976 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.3628. Min Act: -0.1700
Data Index: 1181259 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.3315. Min Act: -0.1700
Data Index: 1533525 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.2690. Min Act: -0.1700
Data Index: 322944 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1753. Min Act: -0.1700
Data Index: 7442750 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1753. Min Act: -0.1700
Data Index: 6130969 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1753. Min Act: -0.1700
Data Index: 1968165 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1440. Min Act: -0.1700
Data Index: 8621580 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1440. Min Act: -0.1692
Data Index: 7535425 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1440. Min Act: -0.1700
Data Index: 4554102 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1128. Min Act: -0.1700
Data Index: 5220403 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1440. Min Act: -0.1700
Data Index: 5015687 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1128. Min Act: -0.1700
Data Index: 3368867 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9878. Min Range: -6.9878
Max Act: 6.1128. Min Act: -0.1700
Data Index: 7512140 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19