Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1244 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7159. Min Range: -9.7159
Max Act: 9.7159. Min Act: -0.1700
Data Index: 7840997 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7159. Min Range: -9.7159
Max Act: 9.0909. Min Act: -0.1700
Data Index: 1963196 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7159. Min Range: -9.7159
Max Act: 9.0284. Min Act: -0.1700
Data Index: 4619574 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.9659. Min Act: -0.1700
Data Index: 8641107 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.9659. Min Act: -0.1700
Data Index: 7519637 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.8409. Min Act: -0.1700
Data Index: 2785183 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.8409. Min Act: -0.1700
Data Index: 3556981 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.7784. Min Act: -0.1700
Data Index: 5791830 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.7159. Min Act: -0.1700
Data Index: 5967513 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.7159. Min Act: -0.1700
Data Index: 8514118 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.7159. Min Act: -0.1700
Data Index: 3544234 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.5909. Min Act: -0.1700
Data Index: 93761 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.7159. Min Act: -0.1700
Data Index: 3194768 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.6534. Min Act: -0.1700
Data Index: 7288747 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.5909. Min Act: -0.1700
Data Index: 4018382 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.5909. Min Act: -0.1700
Data Index: 5932932 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.5284. Min Act: -0.1700
Data Index: 4168289 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.5284. Min Act: -0.1700
Data Index: 6354692 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.5284. Min Act: -0.1700
Data Index: 400958 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7159. Min Range: -9.7159
Max Act: 8.4659. Min Act: -0.1700
Data Index: 3367166 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19