Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4376. Min Act: -0.1677
Data Index: 2039723 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4376. Min Act: -0.1650
Data Index: 7821494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4304. Min Act: -0.1700
Data Index: 8305906 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4304. Min Act: -0.1672
Data Index: 5205526 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4232. Min Act: -0.1698
Data Index: 6975037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4089. Min Act: -0.1695
Data Index: 811625 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4018. Min Act: -0.1700
Data Index: 5848281 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4089. Min Act: -0.1697
Data Index: 1503365 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4089. Min Act: -0.1700
Data Index: 7888771 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4018. Min Act: -0.1700
Data Index: 386632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4089. Min Act: -0.1700
Data Index: 6686331 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3947. Min Act: -0.1663
Data Index: 6444963 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3877. Min Act: -0.1700
Data Index: 3376406 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.4018. Min Act: -0.1698
Data Index: 5772779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3947. Min Act: -0.1671
Data Index: 3963276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3947. Min Act: -0.1691
Data Index: 8499525 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3877. Min Act: -0.1700
Data Index: 7633528 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3808. Min Act: -0.1700
Data Index: 8128713 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3947. Min Act: -0.1672
Data Index: 1221854 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4376. Min Range: -0.4376
Max Act: 0.3877. Min Act: -0.1699
Data Index: 1412575 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19