Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1048 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5200. Min Range: -9.5200
Max Act: 9.5200. Min Act: -0.1700
Data Index: 2724317 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5200. Min Range: -9.5200
Max Act: 9.0825. Min Act: -0.1700
Data Index: 4487740 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.7700. Min Act: -0.1700
Data Index: 6388578 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.3950. Min Act: -0.1700
Data Index: 4893066 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.3950. Min Act: -0.1700
Data Index: 7392382 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.3325. Min Act: -0.1700
Data Index: 1352185 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.3325. Min Act: -0.1700
Data Index: 3918126 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.2075. Min Act: -0.1700
Data Index: 5535928 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.2075. Min Act: -0.1700
Data Index: 962456 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.0825. Min Act: -0.1700
Data Index: 5923912 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.1450. Min Act: -0.1700
Data Index: 3838057 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5200. Min Range: -9.5200
Max Act: 8.0825. Min Act: -0.1700
Data Index: 5765457 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.9888. Min Act: -0.1700
Data Index: 116911 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.9888. Min Act: -0.1700
Data Index: 8041818 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.9263. Min Act: -0.1700
Data Index: 8675436 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.9888. Min Act: -0.1700
Data Index: 439258 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.8950. Min Act: -0.1700
Data Index: 5401471 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.9263. Min Act: -0.1700
Data Index: 2904376 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.9888. Min Act: -0.1700
Data Index: 4335401 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5200. Min Range: -9.5200
Max Act: 7.9575. Min Act: -0.1700
Data Index: 2126901 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19