Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.8620. Min Act: -0.1700
Data Index: 8053411 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.8308. Min Act: -0.1700
Data Index: 7018944 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.7683. Min Act: -0.1700
Data Index: 4282424 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.7370. Min Act: -0.1700
Data Index: 1521046 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.5495. Min Act: -0.1700
Data Index: 2465413 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.5808. Min Act: -0.1700
Data Index: 1250513 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.5183. Min Act: -0.1700
Data Index: 6555170 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.5183. Min Act: -0.1700
Data Index: 881943 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.4245. Min Act: -0.1700
Data Index: 5141317 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3933. Min Act: -0.1700
Data Index: 1904100 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3933. Min Act: -0.1700
Data Index: 1692092 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3620. Min Act: -0.1700
Data Index: 4712801 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3620. Min Act: -0.1700
Data Index: 1786368 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3620. Min Act: -0.1700
Data Index: 698739 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3933. Min Act: -0.1700
Data Index: 4742513 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3620. Min Act: -0.1700
Data Index: 7439396 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.3308. Min Act: -0.1700
Data Index: 8759334 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.2995. Min Act: -0.1700
Data Index: 6810944 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.2683. Min Act: -0.1700
Data Index: 6487155 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8620. Min Range: -6.8620
Max Act: 6.2995. Min Act: -0.1700
Data Index: 5410528 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19