Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5214 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0674. Min Range: -4.0674
Max Act: 4.0674. Min Act: -0.1700
Data Index: 2099552 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9737. Min Act: -0.1700
Data Index: 6933915 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9737. Min Act: -0.1700
Data Index: 6018969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9424. Min Act: -0.1700
Data Index: 128106 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9424. Min Act: -0.1700
Data Index: 6798014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9424. Min Act: -0.1700
Data Index: 2243011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9111. Min Act: -0.1700
Data Index: 6200405 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9111. Min Act: -0.1700
Data Index: 8828749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9111. Min Act: -0.1700
Data Index: 1078971 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9111. Min Act: -0.1700
Data Index: 4669717 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.9111. Min Act: -0.1700
Data Index: 3210395 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8799. Min Act: -0.1700
Data Index: 7005994 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8799. Min Act: -0.1700
Data Index: 2385936 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8799. Min Act: -0.1700
Data Index: 8090597 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8486. Min Act: -0.1700
Data Index: 5961431 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8486. Min Act: -0.1700
Data Index: 5345182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8486. Min Act: -0.1700
Data Index: 2244085 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8486. Min Act: -0.1700
Data Index: 3495980 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8486. Min Act: -0.1700
Data Index: 165927 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0674. Min Range: -4.0674
Max Act: 3.8486. Min Act: -0.1700
Data Index: 6471802 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19