Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.7573. Min Act: -0.1700
Data Index: 3016939 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.5648. Min Act: -0.1700
Data Index: 5558706 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.5001. Min Act: -0.1700
Data Index: 523401 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.5001. Min Act: -0.1700
Data Index: 8660746 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.5163. Min Act: -0.1700
Data Index: 7116618 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.5001. Min Act: -0.1700
Data Index: 2661054 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.5163. Min Act: -0.1700
Data Index: 851316 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4839. Min Act: -0.1700
Data Index: 5321972 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4677. Min Act: -0.1700
Data Index: 5260828 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4352. Min Act: -0.1700
Data Index: 3725686 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4515. Min Act: -0.1700
Data Index: 6453331 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4515. Min Act: -0.1700
Data Index: 5359803 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4352. Min Act: -0.1700
Data Index: 5922068 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4026. Min Act: -0.1700
Data Index: 4474032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.3699. Min Act: -0.1700
Data Index: 714931 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.3863. Min Act: -0.1700
Data Index: 6172640 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4026. Min Act: -0.1700
Data Index: 8073836 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4026. Min Act: -0.1700
Data Index: 6174002 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.3863. Min Act: -0.1700
Data Index: 5006660 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7573. Min Range: -2.7573
Max Act: 2.4026. Min Act: -0.1700
Data Index: 722951 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19