Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4134 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1615. Min Range: -6.1615
Max Act: 6.1615. Min Act: -0.1700
Data Index: 8763174 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.9428. Min Act: -0.1700
Data Index: 4994001 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.7865. Min Act: -0.1700
Data Index: 1130376 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.6615. Min Act: -0.1700
Data Index: 3950993 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.6303. Min Act: -0.1700
Data Index: 8287438 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5990. Min Act: -0.1700
Data Index: 7427761 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5678. Min Act: -0.1700
Data Index: 7949884 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5365. Min Act: -0.1700
Data Index: 2527909 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5365. Min Act: -0.1700
Data Index: 2350952 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5365. Min Act: -0.1700
Data Index: 3795177 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5365. Min Act: -0.1700
Data Index: 5490460 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5678. Min Act: -0.1700
Data Index: 2099848 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5053. Min Act: -0.1700
Data Index: 4012167 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.5053. Min Act: -0.1700
Data Index: 6605393 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.4740. Min Act: -0.1700
Data Index: 7839253 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.4740. Min Act: -0.1700
Data Index: 4240251 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2860024 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.4740. Min Act: -0.1700
Data Index: 68655 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.4740. Min Act: -0.1700
Data Index: 6501554 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1615. Min Range: -6.1615
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2420759 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19