Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.6963. Min Act: -0.1700
Data Index: 4896995 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.6651. Min Act: -0.1694
Data Index: 839078 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.6651. Min Act: -0.1700
Data Index: 403219 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.6026. Min Act: -0.1700
Data Index: 1232895 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5713. Min Act: -0.1700
Data Index: 4096281 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5713. Min Act: -0.1700
Data Index: 8772068 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7082698 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5401. Min Act: -0.1700
Data Index: 2253615 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5713. Min Act: -0.1700
Data Index: 2328674 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5713. Min Act: -0.1700
Data Index: 5501387 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5401. Min Act: -0.1700
Data Index: 8413213 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5401. Min Act: -0.1700
Data Index: 3112516 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5401. Min Act: -0.1700
Data Index: 5343466 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6947162 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5401. Min Act: -0.1700
Data Index: 820553 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6236138 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5088. Min Act: -0.1700
Data Index: 5738707 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5088. Min Act: -0.1700
Data Index: 8705809 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.5088. Min Act: -0.1700
Data Index: 6112949 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6963. Min Range: -5.6963
Max Act: 5.4776. Min Act: -0.1700
Data Index: 2885151 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19