Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4360 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5600. Min Range: -8.5600
Max Act: 8.5600. Min Act: -0.1700
Data Index: 217763 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5600. Min Range: -8.5600
Max Act: 8.0288. Min Act: -0.1700
Data Index: 7163088 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.9663. Min Act: -0.1700
Data Index: 7674251 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.7788. Min Act: -0.1700
Data Index: 4357795 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.7475. Min Act: -0.1700
Data Index: 3882065 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.5288. Min Act: -0.1700
Data Index: 5375932 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.3725. Min Act: -0.1700
Data Index: 1419116 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.3725. Min Act: -0.1700
Data Index: 4410632 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.3413. Min Act: -0.1700
Data Index: 1308165 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.3413. Min Act: -0.1700
Data Index: 8741001 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.3100. Min Act: -0.1700
Data Index: 114200 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.3100. Min Act: -0.1700
Data Index: 3182555 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.3100. Min Act: -0.1700
Data Index: 330986 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.2475. Min Act: -0.1700
Data Index: 4592947 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.2475. Min Act: -0.1700
Data Index: 3734208 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.2475. Min Act: -0.1700
Data Index: 2198571 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.2163. Min Act: -0.1700
Data Index: 7315168 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.1850. Min Act: -0.1700
Data Index: 8259234 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.2163. Min Act: -0.1700
Data Index: 8798223 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5600. Min Range: -8.5600
Max Act: 7.2163. Min Act: -0.1700
Data Index: 253220 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19