Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.2878. Min Act: -0.1700
Data Index: 7724329 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.9753. Min Act: -0.1700
Data Index: 3596317 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.9441. Min Act: -0.1700
Data Index: 126266 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.9128. Min Act: -0.1700
Data Index: 3440968 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.8816. Min Act: -0.1700
Data Index: 973063 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.8816. Min Act: -0.1700
Data Index: 8246049 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.8191. Min Act: -0.1700
Data Index: 5918188 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.7253. Min Act: -0.1700
Data Index: 1629465 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.7253. Min Act: -0.1700
Data Index: 2491214 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.7253. Min Act: -0.1700
Data Index: 3732434 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.7253. Min Act: -0.1700
Data Index: 3742838 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.7253. Min Act: -0.1700
Data Index: 5837349 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6941. Min Act: -0.1700
Data Index: 1314882 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6941. Min Act: -0.1700
Data Index: 2605937 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6941. Min Act: -0.1700
Data Index: 1658377 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6628. Min Act: -0.1700
Data Index: 5012870 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6628. Min Act: -0.1700
Data Index: 2472323 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6628. Min Act: -0.1700
Data Index: 7110078 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6628. Min Act: -0.1700
Data Index: 2513534 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.6316. Min Act: -0.1700
Data Index: 6451531 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19