Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0121. Min Range: -7.0121
Max Act: 7.0121. Min Act: -0.1700
Data Index: 6470602 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.9496. Min Act: -0.1700
Data Index: 4609253 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.9184. Min Act: -0.1700
Data Index: 6309414 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.9184. Min Act: -0.1700
Data Index: 8065379 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.8871. Min Act: -0.1700
Data Index: 4251204 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.8559. Min Act: -0.1700
Data Index: 5028238 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.8246. Min Act: -0.1700
Data Index: 5735846 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.8559. Min Act: -0.1700
Data Index: 181613 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.7934. Min Act: -0.1700
Data Index: 6000761 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.7621. Min Act: -0.1700
Data Index: 4846147 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.7309. Min Act: -0.1700
Data Index: 1019856 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.7309. Min Act: -0.1700
Data Index: 882757 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.7309. Min Act: -0.1700
Data Index: 2221774 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.6996. Min Act: -0.1700
Data Index: 2731094 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.6684. Min Act: -0.1700
Data Index: 7175063 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.6996. Min Act: -0.1700
Data Index: 2234700 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.7309. Min Act: -0.1700
Data Index: 6789408 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.6684. Min Act: -0.1700
Data Index: 8634895 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.6684. Min Act: -0.1700
Data Index: 1891405 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0121. Min Range: -7.0121
Max Act: 6.6684. Min Act: -0.1700
Data Index: 6662680 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19