Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.3411. Min Act: -0.1700
Data Index: 426245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1536. Min Act: -0.1700
Data Index: 1335388 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1224. Min Act: -0.1700
Data Index: 5991174 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1536. Min Act: -0.1700
Data Index: 8133847 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1224. Min Act: -0.1700
Data Index: 3181488 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1224. Min Act: -0.1700
Data Index: 1916429 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1224. Min Act: -0.1700
Data Index: 8289091 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0911. Min Act: -0.1700
Data Index: 5975532 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0911. Min Act: -0.1700
Data Index: 2070184 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0911. Min Act: -0.1700
Data Index: 1552662 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 6353772 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0911. Min Act: -0.1700
Data Index: 2863414 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0286. Min Act: -0.1700
Data Index: 2915194 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 1990672 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 1444870 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 2905772 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 8326265 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 2773537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 7615866 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1695
Data Index: 3468755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19