Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.6513. Min Act: -0.1700
Data Index: 7041794 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.6513. Min Act: -0.1700
Data Index: 3712659 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5730. Min Act: -0.1700
Data Index: 3411685 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5417. Min Act: -0.1700
Data Index: 1183144 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5730. Min Act: -0.1700
Data Index: 6645172 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5574. Min Act: -0.1700
Data Index: 7217493 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5417. Min Act: -0.1700
Data Index: 8537121 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5104. Min Act: -0.1700
Data Index: 1806640 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5261. Min Act: -0.1700
Data Index: 2263324 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4947. Min Act: -0.1700
Data Index: 2007981 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5261. Min Act: -0.1700
Data Index: 4344011 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5104. Min Act: -0.1700
Data Index: 1414426 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.5104. Min Act: -0.1700
Data Index: 1008420 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4947. Min Act: -0.1700
Data Index: 8433908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4791. Min Act: -0.1700
Data Index: 2314310 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4947. Min Act: -0.1700
Data Index: 2457099 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4791. Min Act: -0.1700
Data Index: 586729 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4634. Min Act: -0.1700
Data Index: 4967568 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4947. Min Act: -0.1700
Data Index: 6840647 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6513. Min Range: -3.6513
Max Act: 3.4477. Min Act: -0.1700
Data Index: 6988258 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19