Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4947 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2778. Min Range: -7.2778
Max Act: 7.2778. Min Act: -0.1700
Data Index: 2004998 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2778. Min Range: -7.2778
Max Act: 7.2153. Min Act: -0.1700
Data Index: 2379876 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2778. Min Range: -7.2778
Max Act: 7.1528. Min Act: -0.1700
Data Index: 2379875 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.9653. Min Act: -0.1700
Data Index: 2379859 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.8403. Min Act: -0.1700
Data Index: 7877437 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.7465. Min Act: -0.1700
Data Index: 2379853 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.7153. Min Act: -0.1700
Data Index: 2379864 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.7465. Min Act: -0.1700
Data Index: 348398 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.6840. Min Act: -0.1700
Data Index: 2379852 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.7153. Min Act: -0.1700
Data Index: 2379871 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.6840. Min Act: -0.1700
Data Index: 2379873 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.5903. Min Act: -0.1700
Data Index: 2379857 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.5903. Min Act: -0.1700
Data Index: 6094112 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.5903. Min Act: -0.1700
Data Index: 6368111 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.5590. Min Act: -0.1700
Data Index: 2379855 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 2379867 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 2379870 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 4555326 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.4965. Min Act: -0.1700
Data Index: 4399203 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2778. Min Range: -7.2778
Max Act: 6.4653. Min Act: -0.1700
Data Index: 2379854 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19