Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.3144. Min Act: -0.1700
Data Index: 588229 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.3144. Min Act: -0.1700
Data Index: 3499240 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.2831. Min Act: -0.1700
Data Index: 2673664 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.2519. Min Act: -0.1700
Data Index: 1181074 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.2206. Min Act: -0.1700
Data Index: 3646178 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.2206. Min Act: -0.1700
Data Index: 7680104 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.2206. Min Act: -0.1700
Data Index: 1288311 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1894. Min Act: -0.1700
Data Index: 1138677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1894. Min Act: -0.1700
Data Index: 1143041 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1894. Min Act: -0.1700
Data Index: 7861833 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1894. Min Act: -0.1700
Data Index: 6329899 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1894. Min Act: -0.1700
Data Index: 759826 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1581. Min Act: -0.1700
Data Index: 8550710 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1581. Min Act: -0.1700
Data Index: 2685690 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1894. Min Act: -0.1700
Data Index: 8406024 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1581. Min Act: -0.1700
Data Index: 4052322 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1269. Min Act: -0.1700
Data Index: 5327233 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1269. Min Act: -0.1700
Data Index: 4861436 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1269. Min Act: -0.1700
Data Index: 14597 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3144. Min Range: -6.3144
Max Act: 6.1269. Min Act: -0.1700
Data Index: 6214098 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19