Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0468. Min Range: -4.0468
Max Act: 4.0468. Min Act: -0.1700
Data Index: 5711065 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.9843. Min Act: -0.1700
Data Index: 1986407 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.9530. Min Act: -0.1700
Data Index: 585931 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.9217. Min Act: -0.1700
Data Index: 2137396 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8905. Min Act: -0.1700
Data Index: 5871742 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8905. Min Act: -0.1700
Data Index: 8701450 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8592. Min Act: -0.1700
Data Index: 1484522 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8592. Min Act: -0.1700
Data Index: 1385556 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8592. Min Act: -0.1700
Data Index: 503259 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8592. Min Act: -0.1700
Data Index: 6832938 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8592. Min Act: -0.1700
Data Index: 5564637 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8592. Min Act: -0.1700
Data Index: 3946332 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.7967. Min Act: -0.1700
Data Index: 4672255 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8279. Min Act: -0.1700
Data Index: 5606865 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8279. Min Act: -0.1700
Data Index: 919614 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.8279. Min Act: -0.1700
Data Index: 5361560 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.7967. Min Act: -0.1700
Data Index: 4527806 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.7967. Min Act: -0.1700
Data Index: 3362110 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.7967. Min Act: -0.1700
Data Index: 2345401 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0468. Min Range: -4.0468
Max Act: 3.7967. Min Act: -0.1700
Data Index: 5407274 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19