Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.9459. Min Act: -0.1700
Data Index: 3705431 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.9146. Min Act: -0.1700
Data Index: 4644912 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.8209. Min Act: -0.1700
Data Index: 8022153 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.7584. Min Act: -0.1700
Data Index: 7333541 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.6334. Min Act: -0.1700
Data Index: 2526971 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.6646. Min Act: -0.1700
Data Index: 1372510 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.6334. Min Act: -0.1700
Data Index: 4300620 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.6959. Min Act: -0.1700
Data Index: 3827263 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.5709. Min Act: -0.1700
Data Index: 4775794 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.6021. Min Act: -0.1700
Data Index: 3316361 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.6021. Min Act: -0.1700
Data Index: 3131828 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.6021. Min Act: -0.1700
Data Index: 4583476 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5692956 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.5084. Min Act: -0.1700
Data Index: 3125580 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.5396. Min Act: -0.1700
Data Index: 3180295 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.4771. Min Act: -0.1700
Data Index: 1410080 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.4771. Min Act: -0.1700
Data Index: 5809272 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.5396. Min Act: -0.1700
Data Index: 4846161 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.5084. Min Act: -0.1700
Data Index: 2644567 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9459. Min Range: -5.9459
Max Act: 5.4771. Min Act: -0.1700
Data Index: 1678821 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19