Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2436 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.9842. Min Act: -0.1700
Data Index: 4710447 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.9217. Min Act: -0.1700
Data Index: 7852345 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.9217. Min Act: -0.1700
Data Index: 466947 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.8905. Min Act: -0.1700
Data Index: 8058186 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.8905. Min Act: -0.1700
Data Index: 2136367 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.8592. Min Act: -0.1700
Data Index: 4818006 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.8905. Min Act: -0.1700
Data Index: 2009841 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.8280. Min Act: -0.1700
Data Index: 7249206 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7967. Min Act: -0.1700
Data Index: 3708763 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.8280. Min Act: -0.1700
Data Index: 702742 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7967. Min Act: -0.1700
Data Index: 2271495 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7655. Min Act: -0.1700
Data Index: 5393034 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7342. Min Act: -0.1700
Data Index: 202254 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7342. Min Act: -0.1700
Data Index: 3719154 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7342. Min Act: -0.1700
Data Index: 957429 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7342. Min Act: -0.1700
Data Index: 134622 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7342. Min Act: -0.1700
Data Index: 3418548 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.6717. Min Act: -0.1700
Data Index: 1560020 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.7030. Min Act: -0.1700
Data Index: 1785900 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9842. Min Range: -6.9842
Max Act: 6.6717. Min Act: -0.1700
Data Index: 2605559 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19