Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4534 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.3137. Min Act: -0.1700
Data Index: 8239796 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.2980. Min Act: -0.1700
Data Index: 826637 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.0935. Min Act: -0.1700
Data Index: 5060571 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.0619. Min Act: -0.1700
Data Index: 3423497 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.0619. Min Act: -0.1700
Data Index: 1528102 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.0619. Min Act: -0.1700
Data Index: 1411428 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.0304. Min Act: -0.1700
Data Index: 5144443 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3137. Min Range: -3.3137
Max Act: 3.0146. Min Act: -0.1680
Data Index: 3137083 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9988. Min Act: -0.1700
Data Index: 8293803 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9830. Min Act: -0.1700
Data Index: 4476174 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9830. Min Act: -0.1700
Data Index: 6752799 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9830. Min Act: -0.1700
Data Index: 8713719 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9830. Min Act: -0.1700
Data Index: 6822327 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9830. Min Act: -0.1700
Data Index: 5994781 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9513. Min Act: -0.1700
Data Index: 2829351 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9513. Min Act: -0.1700
Data Index: 7904874 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9513. Min Act: -0.1699
Data Index: 5566803 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9513. Min Act: -0.1700
Data Index: 8516496 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9672. Min Act: -0.1700
Data Index: 5882187 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3137. Min Range: -3.3137
Max Act: 2.9355. Min Act: -0.1700
Data Index: 392062 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19