Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.7140. Min Act: -0.1700
Data Index: 7132730 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.6515. Min Act: -0.1700
Data Index: 6224527 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.4952. Min Act: -0.1700
Data Index: 5312171 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.4952. Min Act: -0.1700
Data Index: 986898 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.4640. Min Act: -0.1700
Data Index: 4945917 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.4952. Min Act: -0.1700
Data Index: 4533962 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.4327. Min Act: -0.1700
Data Index: 6217016 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.4015. Min Act: -0.1700
Data Index: 8605797 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.4015. Min Act: -0.1700
Data Index: 656885 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.3702. Min Act: -0.1700
Data Index: 5388104 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.3702. Min Act: -0.1700
Data Index: 1992775 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.3390. Min Act: -0.1700
Data Index: 2085498 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.3702. Min Act: -0.1700
Data Index: 8775171 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.3390. Min Act: -0.1700
Data Index: 5679735 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.3077. Min Act: -0.1700
Data Index: 8722363 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.3077. Min Act: -0.1700
Data Index: 6706317 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.2765. Min Act: -0.1700
Data Index: 6324310 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.2452. Min Act: -0.1700
Data Index: 8233231 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.2452. Min Act: -0.1700
Data Index: 5156206 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7140. Min Range: -7.7140
Max Act: 7.2140. Min Act: -0.1700
Data Index: 1414469 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19