Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8525. Min Act: -0.1700
Data Index: 4593957 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8366. Min Act: -0.1700
Data Index: 5962511 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8684. Min Act: -0.1700
Data Index: 5988448 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8207. Min Act: -0.1700
Data Index: 2490958 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8207. Min Act: -0.1700
Data Index: 8036236 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8048. Min Act: -0.1700
Data Index: 3140930 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8048. Min Act: -0.1700
Data Index: 8365107 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.8048. Min Act: -0.1700
Data Index: 6254771 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7730. Min Act: -0.1700
Data Index: 8501743 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7410. Min Act: -0.1700
Data Index: 1197718 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7730. Min Act: -0.1700
Data Index: 8320419 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7570. Min Act: -0.1700
Data Index: 3928769 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7570. Min Act: -0.1700
Data Index: 8829284 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7410. Min Act: -0.1700
Data Index: 6552201 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7410. Min Act: -0.1700
Data Index: 5286522 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7410. Min Act: -0.1700
Data Index: 5072529 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7410. Min Act: -0.1700
Data Index: 7072397 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7091. Min Act: -0.1700
Data Index: 6385336 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7091. Min Act: -0.1700
Data Index: 8191964 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8684. Min Range: -2.8684
Max Act: 2.7091. Min Act: -0.1700
Data Index: 8228837 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19