Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.5393. Min Act: -0.1700
Data Index: 4122796 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.3518. Min Act: -0.1700
Data Index: 6571508 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.2580. Min Act: -0.1700
Data Index: 5627962 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.2268. Min Act: -0.1700
Data Index: 4103462 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.2268. Min Act: -0.1700
Data Index: 867948 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.1642. Min Act: -0.1700
Data Index: 8726152 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.0705. Min Act: -0.1700
Data Index: 8769954 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.0392. Min Act: -0.1700
Data Index: 2552042 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.0392. Min Act: -0.1700
Data Index: 3769387 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.0392. Min Act: -0.1700
Data Index: 4557837 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.0080. Min Act: -0.1700
Data Index: 6518864 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9767. Min Act: -0.1700
Data Index: 6373826 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9767. Min Act: -0.1700
Data Index: 6119116 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9767. Min Act: -0.1700
Data Index: 1268030 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9767. Min Act: -0.1700
Data Index: 2416015 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5393. Min Range: -4.5393
Max Act: 4.0080. Min Act: -0.1700
Data Index: 1037799 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9454. Min Act: -0.1700
Data Index: 7774829 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9454. Min Act: -0.1700
Data Index: 1059454 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9454. Min Act: -0.1700
Data Index: 3297908 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5393. Min Range: -4.5393
Max Act: 3.9142. Min Act: -0.1700
Data Index: 1299791 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19