Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2178 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.5726. Min Act: -0.1700
Data Index: 5647721 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.2288. Min Act: -0.1700
Data Index: 3612263 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.1663. Min Act: -0.1700
Data Index: 4237677 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.1351. Min Act: -0.1700
Data Index: 8156077 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 2667098 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0726. Min Act: -0.1700
Data Index: 7877451 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 394966 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 5504327 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 5100734 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 8818780 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 7285806 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0100. Min Act: -0.1700
Data Index: 2345901 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0100. Min Act: -0.1700
Data Index: 1936017 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5726. Min Range: -4.5726
Max Act: 4.0100. Min Act: -0.1700
Data Index: 4293150 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5726. Min Range: -4.5726
Max Act: 3.9788. Min Act: -0.1700
Data Index: 5192740 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5726. Min Range: -4.5726
Max Act: 3.9788. Min Act: -0.1700
Data Index: 21319 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5726. Min Range: -4.5726
Max Act: 3.9475. Min Act: -0.1700
Data Index: 611327 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5726. Min Range: -4.5726
Max Act: 3.9475. Min Act: -0.1700
Data Index: 6850981 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5726. Min Range: -4.5726
Max Act: 3.9475. Min Act: -0.1700
Data Index: 5821382 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5726. Min Range: -4.5726
Max Act: 3.9788. Min Act: -0.1700
Data Index: 3107618 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19