Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5369 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4123. Min Range: -6.4123
Max Act: 6.4123. Min Act: -0.1700
Data Index: 2354231 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4123. Min Range: -6.4123
Max Act: 6.1623. Min Act: -0.1700
Data Index: 2354233 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4123. Min Range: -6.4123
Max Act: 6.0060. Min Act: -0.1700
Data Index: 2354235 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.9123. Min Act: -0.1700
Data Index: 916194 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.8498. Min Act: -0.1700
Data Index: 4719965 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.8498. Min Act: -0.1700
Data Index: 2354237 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.7873. Min Act: -0.1700
Data Index: 4499660 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.7873. Min Act: -0.1700
Data Index: 2740583 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.6623. Min Act: -0.1700
Data Index: 5163109 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.6935. Min Act: -0.1700
Data Index: 5414236 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.6623. Min Act: -0.1700
Data Index: 1921160 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5998. Min Act: -0.1700
Data Index: 4243074 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5685. Min Act: -0.1700
Data Index: 3897626 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5685. Min Act: -0.1700
Data Index: 2308488 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5373. Min Act: -0.1700
Data Index: 2504853 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5373. Min Act: -0.1700
Data Index: 307404 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5373. Min Act: -0.1700
Data Index: 8281226 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5373. Min Act: -0.1700
Data Index: 2354236 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5373. Min Act: -0.1700
Data Index: 1373478 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4123. Min Range: -6.4123
Max Act: 5.5373. Min Act: -0.1700
Data Index: 5455024 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19