Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5290 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2904. Min Range: -6.2904
Max Act: 6.2904. Min Act: -0.1700
Data Index: 2630046 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2904. Min Range: -6.2904
Max Act: 6.0716. Min Act: -0.1700
Data Index: 4196744 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2904. Min Range: -6.2904
Max Act: 6.0091. Min Act: -0.1700
Data Index: 2790965 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.9466. Min Act: -0.1700
Data Index: 2377302 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.8216. Min Act: -0.1700
Data Index: 2446599 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.7904. Min Act: -0.1700
Data Index: 6641758 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.7591. Min Act: -0.1700
Data Index: 5822948 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.7591. Min Act: -0.1700
Data Index: 725302 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.7279. Min Act: -0.1700
Data Index: 6981583 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.7279. Min Act: -0.1700
Data Index: 755880 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.7279. Min Act: -0.1700
Data Index: 2753862 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6966. Min Act: -0.1700
Data Index: 842460 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6966. Min Act: -0.1700
Data Index: 5755711 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6341. Min Act: -0.1700
Data Index: 3648939 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6654. Min Act: -0.1700
Data Index: 39919 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6654. Min Act: -0.1700
Data Index: 3480294 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6654. Min Act: -0.1700
Data Index: 6345093 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6654. Min Act: -0.1700
Data Index: 2606690 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6654. Min Act: -0.1700
Data Index: 3166967 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2904. Min Range: -6.2904
Max Act: 5.6341. Min Act: -0.1700
Data Index: 5020153 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19