Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1158 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6801. Min Range: -7.6801
Max Act: 7.6801. Min Act: -0.1700
Data Index: 4920835 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6801. Min Range: -7.6801
Max Act: 7.3676. Min Act: -0.1700
Data Index: 4920830 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6801. Min Range: -7.6801
Max Act: 7.2426. Min Act: -0.1700
Data Index: 1187912 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6801. Min Range: -7.6801
Max Act: 7.0551. Min Act: -0.1700
Data Index: 5717447 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6801. Min Range: -7.6801
Max Act: 7.0864. Min Act: -0.1700
Data Index: 2872241 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.8676. Min Act: -0.1700
Data Index: 7990496 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.8676. Min Act: -0.1700
Data Index: 3844403 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.8051. Min Act: -0.1700
Data Index: 5302138 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.8051. Min Act: -0.1700
Data Index: 4149432 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.7426. Min Act: -0.1700
Data Index: 2184762 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.7114. Min Act: -0.1700
Data Index: 4330035 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.7426. Min Act: -0.1700
Data Index: 282255 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.7114. Min Act: -0.1700
Data Index: 7578454 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.7114. Min Act: -0.1700
Data Index: 1707466 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.7114. Min Act: -0.1700
Data Index: 4075516 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.7114. Min Act: -0.1700
Data Index: 7711065 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.6801. Min Act: -0.1700
Data Index: 6799510 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.6801. Min Act: -0.1700
Data Index: 5808754 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.6801. Min Act: -0.1700
Data Index: 4199864 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6801. Min Range: -7.6801
Max Act: 6.6489. Min Act: -0.1700
Data Index: 1812185 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19