Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5760 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0006. Min Range: -6.0006
Max Act: 6.0006. Min Act: -0.1700
Data Index: 7352078 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9693. Min Act: -0.1700
Data Index: 6850717 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9693. Min Act: -0.1700
Data Index: 4119204 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0006. Min Range: -6.0006
Max Act: 6.0006. Min Act: -0.1700
Data Index: 432034 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9693. Min Act: -0.1700
Data Index: 7095480 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4665743 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9693. Min Act: -0.1700
Data Index: 5760640 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9381. Min Act: -0.1700
Data Index: 4315895 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9381. Min Act: -0.1700
Data Index: 7089391 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9068. Min Act: -0.1700
Data Index: 3540833 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9068. Min Act: -0.1700
Data Index: 5674269 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.9068. Min Act: -0.1700
Data Index: 8099261 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8756. Min Act: -0.1700
Data Index: 8375248 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8756. Min Act: -0.1700
Data Index: 4286891 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8756. Min Act: -0.1700
Data Index: 2802138 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8756. Min Act: -0.1700
Data Index: 6896356 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8756. Min Act: -0.1700
Data Index: 5134577 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1615238 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8131. Min Act: -0.1700
Data Index: 2353898 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0006. Min Range: -6.0006
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4119193 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19