Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0983. Min Range: -7.0983
Max Act: 7.0983. Min Act: -0.1700
Data Index: 7347784 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0983. Min Range: -7.0983
Max Act: 7.0983. Min Act: -0.1700
Data Index: 199355 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0983. Min Range: -7.0983
Max Act: 7.0045. Min Act: -0.1700
Data Index: 7861343 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0983. Min Range: -7.0983
Max Act: 7.0358. Min Act: -0.1700
Data Index: 7339013 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0983. Min Range: -7.0983
Max Act: 7.0045. Min Act: -0.1700
Data Index: 5431470 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0983. Min Range: -7.0983
Max Act: 7.0045. Min Act: -0.1700
Data Index: 3834099 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.9733. Min Act: -0.1700
Data Index: 1860786 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.9420. Min Act: -0.1700
Data Index: 7177287 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.9420. Min Act: -0.1700
Data Index: 7260652 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.9108. Min Act: -0.1700
Data Index: 5694634 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.9733. Min Act: -0.1700
Data Index: 4233882 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8795. Min Act: -0.1700
Data Index: 8326412 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8795. Min Act: -0.1700
Data Index: 3825347 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8795. Min Act: -0.1700
Data Index: 1688064 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8795. Min Act: -0.1700
Data Index: 2388025 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8483. Min Act: -0.1700
Data Index: 586104 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8170. Min Act: -0.1700
Data Index: 1291647 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8483. Min Act: -0.1700
Data Index: 2008338 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8170. Min Act: -0.1700
Data Index: 4004534 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0983. Min Range: -7.0983
Max Act: 6.8170. Min Act: -0.1700
Data Index: 6549105 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19