Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.7650. Min Act: -0.1700
Data Index: 6850151 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.5775. Min Act: -0.1700
Data Index: 4778669 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.4837. Min Act: -0.1700
Data Index: 5995650 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.4212. Min Act: -0.1700
Data Index: 8424085 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.3900. Min Act: -0.1700
Data Index: 4853789 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.3587. Min Act: -0.1700
Data Index: 4895197 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.3275. Min Act: -0.1700
Data Index: 2364240 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.3587. Min Act: -0.1700
Data Index: 5738651 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.2650. Min Act: -0.1700
Data Index: 5629133 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.2650. Min Act: -0.1700
Data Index: 7633933 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.2025. Min Act: -0.1700
Data Index: 7693266 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.2025. Min Act: -0.1700
Data Index: 4184814 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.2025. Min Act: -0.1700
Data Index: 5644309 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.2025. Min Act: -0.1700
Data Index: 7599455 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.1712. Min Act: -0.1700
Data Index: 4646274 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.1400. Min Act: -0.1700
Data Index: 2015593 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.1712. Min Act: -0.1700
Data Index: 5475727 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.1400. Min Act: -0.1700
Data Index: 1728074 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.0775. Min Act: -0.1700
Data Index: 4762854 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7650. Min Range: -6.7650
Max Act: 6.1087. Min Act: -0.1700
Data Index: 1791176 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19