Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1614 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.8706. Min Act: -0.1700
Data Index: 4013706 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.7144. Min Act: -0.1700
Data Index: 4892089 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.7456. Min Act: -0.1700
Data Index: 7966598 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.7144. Min Act: -0.1700
Data Index: 4449475 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.6519. Min Act: -0.1700
Data Index: 8019960 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.6519. Min Act: -0.1700
Data Index: 2308405 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.6519. Min Act: -0.1700
Data Index: 7665201 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.6206. Min Act: -0.1700
Data Index: 5318328 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.5581. Min Act: -0.1700
Data Index: 5350636 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.5581. Min Act: -0.1700
Data Index: 5323831 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.5581. Min Act: -0.1700
Data Index: 3650598 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.4956. Min Act: -0.1700
Data Index: 6138972 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.5269. Min Act: -0.1700
Data Index: 4705198 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.5269. Min Act: -0.1700
Data Index: 7697008 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.4956. Min Act: -0.1700
Data Index: 7354394 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.5269. Min Act: -0.1700
Data Index: 2686956 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.4644. Min Act: -0.1700
Data Index: 8199320 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.4956. Min Act: -0.1700
Data Index: 4818226 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.4956. Min Act: -0.1700
Data Index: 2932990 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8706. Min Range: -5.8706
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5769164 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19