Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.5032. Min Act: -0.1700
Data Index: 161092 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.4718. Min Act: -0.1700
Data Index: 6277415 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.4248. Min Act: -0.1700
Data Index: 5889691 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3935. Min Act: -0.1700
Data Index: 7051091 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3778. Min Act: -0.1700
Data Index: 5896909 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3621. Min Act: -0.1700
Data Index: 1085912 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3621. Min Act: -0.1700
Data Index: 6266417 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3621. Min Act: -0.1700
Data Index: 3007877 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3464. Min Act: -0.1700
Data Index: 8153560 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3307. Min Act: -0.1700
Data Index: 838339 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3150. Min Act: -0.1700
Data Index: 6307028 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3150. Min Act: -0.1700
Data Index: 5571190 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.3150. Min Act: -0.1700
Data Index: 5471998 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.2993. Min Act: -0.1700
Data Index: 8638589 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.2836. Min Act: -0.1700
Data Index: 3715829 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.2836. Min Act: -0.1700
Data Index: 681837 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.2836. Min Act: -0.1700
Data Index: 4432442 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.2836. Min Act: -0.1700
Data Index: 1383988 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.2836. Min Act: -0.1700
Data Index: 7862388 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5032. Min Range: -3.5032
Max Act: 3.2679. Min Act: -0.1700
Data Index: 5408454 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19