Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 748 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.9140. Min Act: -0.1700
Data Index: 5802179 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.7265. Min Act: -0.1700
Data Index: 3339859 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.6015. Min Act: -0.1700
Data Index: 7571401 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.6015. Min Act: -0.1700
Data Index: 7164768 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.5390. Min Act: -0.1700
Data Index: 4679499 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.5390. Min Act: -0.1700
Data Index: 4749122 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.5390. Min Act: -0.1700
Data Index: 8405259 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.5390. Min Act: -0.1700
Data Index: 7632449 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.5390. Min Act: -0.1700
Data Index: 393112 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4765. Min Act: -0.1700
Data Index: 8793897 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4765. Min Act: -0.1700
Data Index: 2306373 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4765. Min Act: -0.1700
Data Index: 2616435 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4765. Min Act: -0.1700
Data Index: 2343541 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4140. Min Act: -0.1700
Data Index: 2106951 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4765. Min Act: -0.1700
Data Index: 6639370 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4765. Min Act: -0.1700
Data Index: 2390893 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4140. Min Act: -0.1700
Data Index: 1041087 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.3515. Min Act: -0.1700
Data Index: 5411036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4140. Min Act: -0.1700
Data Index: 2086134 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9140. Min Range: -8.9140
Max Act: 8.4765. Min Act: -0.1700
Data Index: 4010505 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19