Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.7803. Min Range: -10.7803
Max Act: 10.7803. Min Act: -0.1700
Data Index: 7042702 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7803. Min Range: -10.7803
Max Act: 10.6553. Min Act: -0.1697
Data Index: 8528862 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7803. Min Range: -10.7803
Max Act: 10.3428. Min Act: -0.1700
Data Index: 824444 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.9678. Min Act: -0.1700
Data Index: 5755060 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.7803. Min Act: -0.1700
Data Index: 8385773 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.8428. Min Act: -0.1700
Data Index: 8528863 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.7803. Min Act: -0.1700
Data Index: 6501178 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.8428. Min Act: -0.1700
Data Index: 1865082 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.7803. Min Act: -0.1700
Data Index: 2605993 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.8428. Min Act: -0.1700
Data Index: 2338407 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.7803. Min Act: -0.1700
Data Index: 8698587 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.7803. Min Act: -0.1699
Data Index: 4582924 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.6553. Min Act: -0.1699
Data Index: 2463568 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.5928. Min Act: -0.1700
Data Index: 7192754 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.6553. Min Act: -0.1700
Data Index: 877066 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.6553. Min Act: -0.1700
Data Index: 2739439 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.5303. Min Act: -0.1700
Data Index: 7936706 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.5303. Min Act: -0.1700
Data Index: 7839744 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.4053. Min Act: -0.1700
Data Index: 6967489 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7803. Min Range: -10.7803
Max Act: 9.4053. Min Act: -0.1700
Data Index: 7563678 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19