Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.4768. Min Act: -0.1700
Data Index: 6891141 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.4768. Min Act: -0.1700
Data Index: 5773754 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.2268. Min Act: -0.1700
Data Index: 1108170 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.2893. Min Act: -0.1700
Data Index: 6516166 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.2893. Min Act: -0.1700
Data Index: 7342976 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.2893. Min Act: -0.1700
Data Index: 8395597 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.1956. Min Act: -0.1700
Data Index: 6811573 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.1643. Min Act: -0.1700
Data Index: 2505557 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.2581. Min Act: -0.1700
Data Index: 7342966 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.1018. Min Act: -0.1700
Data Index: 8118642 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.1331. Min Act: -0.1700
Data Index: 6109837 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.1018. Min Act: -0.1700
Data Index: 5817026 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.1331. Min Act: -0.1700
Data Index: 3604976 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.0393. Min Act: -0.1700
Data Index: 5817019 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4768. Min Range: -8.4768
Max Act: 7.9456. Min Act: -0.1700
Data Index: 7342980 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4768. Min Range: -8.4768
Max Act: 8.0081. Min Act: -0.1700
Data Index: 8395592 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4768. Min Range: -8.4768
Max Act: 7.9768. Min Act: -0.1700
Data Index: 6471381 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4768. Min Range: -8.4768
Max Act: 7.8518. Min Act: -0.1700
Data Index: 5161275 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4768. Min Range: -8.4768
Max Act: 7.8831. Min Act: -0.1700
Data Index: 5151001 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4768. Min Range: -8.4768
Max Act: 7.8831. Min Act: -0.1700
Data Index: 7926807 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19