Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1615 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.5108. Min Act: -0.1700
Data Index: 8412434 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.5108. Min Act: -0.1700
Data Index: 7577249 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.2296. Min Act: -0.1700
Data Index: 6859574 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.2608. Min Act: -0.1700
Data Index: 445552 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.2296. Min Act: -0.1700
Data Index: 6311855 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.2296. Min Act: -0.1700
Data Index: 4614629 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1983. Min Act: -0.1700
Data Index: 5173302 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1983. Min Act: -0.1700
Data Index: 5717932 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1983. Min Act: -0.1700
Data Index: 3543321 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1983. Min Act: -0.1700
Data Index: 7151715 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1671. Min Act: -0.1700
Data Index: 2395587 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1671. Min Act: -0.1700
Data Index: 5807383 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1671. Min Act: -0.1700
Data Index: 2232245 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1671. Min Act: -0.1700
Data Index: 1174958 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1671. Min Act: -0.1700
Data Index: 8416520 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1358. Min Act: -0.1700
Data Index: 8596875 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1358. Min Act: -0.1700
Data Index: 1971170 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1358. Min Act: -0.1700
Data Index: 350549 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1046. Min Act: -0.1700
Data Index: 3631127 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5108. Min Range: -5.5108
Max Act: 5.1046. Min Act: -0.1700
Data Index: 7356287 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19