Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.6449. Min Act: -0.1700
Data Index: 972942 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.4886. Min Act: -0.1700
Data Index: 5752447 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.4261. Min Act: -0.1700
Data Index: 6841971 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.3949. Min Act: -0.1700
Data Index: 7233100 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.3636. Min Act: -0.1700
Data Index: 1573864 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.3324. Min Act: -0.1700
Data Index: 282814 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.3011. Min Act: -0.1700
Data Index: 410264 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.3011. Min Act: -0.1700
Data Index: 2030112 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2699. Min Act: -0.1700
Data Index: 7382334 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2699. Min Act: -0.1700
Data Index: 8046385 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2699. Min Act: -0.1700
Data Index: 68622 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2074. Min Act: -0.1700
Data Index: 1070143 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2386. Min Act: -0.1700
Data Index: 330794 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2386. Min Act: -0.1700
Data Index: 8472809 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.1761. Min Act: -0.1700
Data Index: 3746281 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2074. Min Act: -0.1700
Data Index: 6525805 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2386. Min Act: -0.1700
Data Index: 6457000 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2074. Min Act: -0.1700
Data Index: 6380170 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2074. Min Act: -0.1700
Data Index: 62388 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6449. Min Range: -5.6449
Max Act: 5.2074. Min Act: -0.1700
Data Index: 4610525 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19