Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.8042. Min Act: -0.1700
Data Index: 7890474 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.8042. Min Act: -0.1700
Data Index: 915885 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.8042. Min Act: -0.1700
Data Index: 6971868 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.7417. Min Act: -0.1700
Data Index: 7305625 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.7104. Min Act: -0.1700
Data Index: 7346075 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.7104. Min Act: -0.1700
Data Index: 5142103 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.7104. Min Act: -0.1700
Data Index: 996196 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6791. Min Act: -0.1700
Data Index: 4673176 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6635. Min Act: -0.1700
Data Index: 1746730 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6478. Min Act: -0.1700
Data Index: 7619969 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6322. Min Act: -0.1700
Data Index: 3232787 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6478. Min Act: -0.1700
Data Index: 7519061 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6322. Min Act: -0.1700
Data Index: 4487216 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6322. Min Act: -0.1700
Data Index: 186666 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6165. Min Act: -0.1700
Data Index: 8830545 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6322. Min Act: -0.1700
Data Index: 4086086 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6322. Min Act: -0.1700
Data Index: 8347639 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6322. Min Act: -0.1700
Data Index: 3900340 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6165. Min Act: -0.1700
Data Index: 7567623 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8042. Min Range: -3.8042
Max Act: 3.6009. Min Act: -0.1700
Data Index: 2556788 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19