Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7312. Min Range: -6.7312
Max Act: 6.7312. Min Act: -0.1700
Data Index: 4727765 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7312. Min Range: -6.7312
Max Act: 6.4812. Min Act: -0.1700
Data Index: 4250990 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7312. Min Range: -6.7312
Max Act: 6.3874. Min Act: -0.1700
Data Index: 6506495 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7312. Min Range: -6.7312
Max Act: 6.1999. Min Act: -0.1700
Data Index: 6626789 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7312. Min Range: -6.7312
Max Act: 6.0437. Min Act: -0.1700
Data Index: 337764 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.9812. Min Act: -0.1700
Data Index: 3137188 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.8562. Min Act: -0.1700
Data Index: 2621169 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.8874. Min Act: -0.1700
Data Index: 4955312 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.8874. Min Act: -0.1700
Data Index: 1381208 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.9187. Min Act: -0.1700
Data Index: 5082861 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.8562. Min Act: -0.1700
Data Index: 459920 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.8249. Min Act: -0.1700
Data Index: 7380452 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.7312. Min Act: -0.1700
Data Index: 6196585 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.7624. Min Act: -0.1700
Data Index: 6451351 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.7624. Min Act: -0.1700
Data Index: 3015522 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.7624. Min Act: -0.1700
Data Index: 1579020 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.6999. Min Act: -0.1700
Data Index: 7209879 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.7312. Min Act: -0.1700
Data Index: 1672422 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.7312. Min Act: -0.1700
Data Index: 4107111 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7312. Min Range: -6.7312
Max Act: 5.6999. Min Act: -0.1700
Data Index: 6949485 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19