Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.9656. Min Act: -0.1700
Data Index: 5841598 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.9656. Min Act: -0.1700
Data Index: 4877812 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8718. Min Act: -0.1700
Data Index: 6744188 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8718. Min Act: -0.1700
Data Index: 4411846 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8718. Min Act: -0.1700
Data Index: 5221897 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8405. Min Act: -0.1700
Data Index: 803881 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8405. Min Act: -0.1700
Data Index: 4610172 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7780. Min Act: -0.1700
Data Index: 376013 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8718. Min Act: -0.1700
Data Index: 7461809 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8092. Min Act: -0.1700
Data Index: 3163472 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8405. Min Act: -0.1700
Data Index: 6696377 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8092. Min Act: -0.1700
Data Index: 2784658 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.8092. Min Act: -0.1700
Data Index: 1280601 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7780. Min Act: -0.1700
Data Index: 262677 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7780. Min Act: -0.1700
Data Index: 1282199 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7623. Min Act: -0.1700
Data Index: 7315375 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7780. Min Act: -0.1700
Data Index: 6922088 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7623. Min Act: -0.1700
Data Index: 4237608 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7780. Min Act: -0.1700
Data Index: 3976065 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9656. Min Range: -3.9656
Max Act: 3.7780. Min Act: -0.1700
Data Index: 252134 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19