Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.1612. Min Act: -0.1700
Data Index: 3677298 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0987. Min Act: -0.1700
Data Index: 7839800 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0050. Min Act: -0.1697
Data Index: 5923948 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9737. Min Act: -0.1700
Data Index: 7088445 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0050. Min Act: -0.1698
Data Index: 6598092 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9425. Min Act: -0.1700
Data Index: 2944795 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9737. Min Act: -0.1700
Data Index: 371908 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9425. Min Act: -0.1700
Data Index: 40138 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9112. Min Act: -0.1700
Data Index: 2913514 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9112. Min Act: -0.1700
Data Index: 4776794 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9112. Min Act: -0.1700
Data Index: 4749669 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9112. Min Act: -0.1700
Data Index: 6123421 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9112. Min Act: -0.1700
Data Index: 5607235 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8800. Min Act: -0.1699
Data Index: 2231568 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8800. Min Act: -0.1699
Data Index: 5429941 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8800. Min Act: -0.1686
Data Index: 2973290 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8175. Min Act: -0.1700
Data Index: 3001341 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8175. Min Act: -0.1700
Data Index: 906963 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8487. Min Act: -0.1700
Data Index: 5517525 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8800. Min Act: -0.1700
Data Index: 3738235 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19