Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4437 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.8452. Min Act: -0.1700
Data Index: 2500439 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.8139. Min Act: -0.1700
Data Index: 4285172 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.8139. Min Act: -0.1700
Data Index: 7342750 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.8139. Min Act: -0.1700
Data Index: 6529044 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.7827. Min Act: -0.1700
Data Index: 1452945 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.7514. Min Act: -0.1700
Data Index: 2322362 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.6264. Min Act: -0.1700
Data Index: 1411253 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.6264. Min Act: -0.1700
Data Index: 3644562 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5952. Min Act: -0.1700
Data Index: 7041937 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5639. Min Act: -0.1700
Data Index: 1084631 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5327. Min Act: -0.1700
Data Index: 5185373 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5014. Min Act: -0.1700
Data Index: 7883822 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5327. Min Act: -0.1700
Data Index: 7747954 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5014. Min Act: -0.1700
Data Index: 2347133 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4702. Min Act: -0.1700
Data Index: 6720301 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5014. Min Act: -0.1700
Data Index: 7625014 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4389. Min Act: -0.1700
Data Index: 1559767 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4389. Min Act: -0.1700
Data Index: 4749525 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4389. Min Act: -0.1700
Data Index: 106507 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4389. Min Act: -0.1700
Data Index: 7421162 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19