Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2504 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.3704. Min Act: -0.1700
Data Index: 4768686 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.2454. Min Act: -0.1700
Data Index: 4220596 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.1204. Min Act: -0.1700
Data Index: 2976995 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0891. Min Act: -0.1700
Data Index: 5265240 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0579. Min Act: -0.1700
Data Index: 2095832 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0891. Min Act: -0.1700
Data Index: 5034317 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0266. Min Act: -0.1700
Data Index: 330752 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0579. Min Act: -0.1700
Data Index: 146355 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0891. Min Act: -0.1700
Data Index: 7661729 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0266. Min Act: -0.1700
Data Index: 1101297 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9953. Min Act: -0.1700
Data Index: 3101970 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9953. Min Act: -0.1700
Data Index: 2761957 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3704. Min Range: -4.3704
Max Act: 4.0266. Min Act: -0.1700
Data Index: 45502 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9953. Min Act: -0.1700
Data Index: 375263 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9641. Min Act: -0.1700
Data Index: 5775801 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9015. Min Act: -0.1700
Data Index: 1341803 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9015. Min Act: -0.1700
Data Index: 2495465 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9015. Min Act: -0.1700
Data Index: 3900521 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9015. Min Act: -0.1700
Data Index: 3339900 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3704. Min Range: -4.3704
Max Act: 3.9015. Min Act: -0.1700
Data Index: 5265233 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19