Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2056. Min Range: -7.2056
Max Act: 7.2056. Min Act: -0.1700
Data Index: 477886 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2056. Min Range: -7.2056
Max Act: 7.2056. Min Act: -0.1700
Data Index: 466746 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2056. Min Range: -7.2056
Max Act: 7.0806. Min Act: -0.1700
Data Index: 841029 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2056. Min Range: -7.2056
Max Act: 7.0806. Min Act: -0.1700
Data Index: 3367893 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2056. Min Range: -7.2056
Max Act: 7.0181. Min Act: -0.1700
Data Index: 7763722 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.9869. Min Act: -0.1700
Data Index: 4799283 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.8931. Min Act: -0.1700
Data Index: 2676350 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.8931. Min Act: -0.1700
Data Index: 1228027 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.8619. Min Act: -0.1700
Data Index: 8448063 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.8306. Min Act: -0.1700
Data Index: 4542061 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7994. Min Act: -0.1700
Data Index: 1406860 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7681. Min Act: -0.1700
Data Index: 5840322 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7994. Min Act: -0.1700
Data Index: 4140442 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7056. Min Act: -0.1700
Data Index: 1729707 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7369. Min Act: -0.1700
Data Index: 4212647 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7369. Min Act: -0.1700
Data Index: 6035542 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7681. Min Act: -0.1700
Data Index: 3358204 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7369. Min Act: -0.1700
Data Index: 3230159 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7056. Min Act: -0.1700
Data Index: 2918139 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2056. Min Range: -7.2056
Max Act: 6.7369. Min Act: -0.1700
Data Index: 3008132 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19