Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0663. Min Range: -8.0663
Max Act: 8.0663. Min Act: -0.1700
Data Index: 6413977 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.9100. Min Act: -0.1700
Data Index: 5413341 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.7538. Min Act: -0.1700
Data Index: 7268465 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.6913. Min Act: -0.1700
Data Index: 8641702 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.6913. Min Act: -0.1700
Data Index: 387358 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.6288. Min Act: -0.1700
Data Index: 1894385 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.5663. Min Act: -0.1700
Data Index: 3402625 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.5975. Min Act: -0.1700
Data Index: 6781629 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.3475. Min Act: -0.1700
Data Index: 8258424 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.3163. Min Act: -0.1700
Data Index: 1083137 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.2850. Min Act: -0.1700
Data Index: 1405266 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.1913. Min Act: -0.1700
Data Index: 1917403 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.1600. Min Act: -0.1700
Data Index: 2754018 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.0975. Min Act: -0.1700
Data Index: 5634372 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.1288. Min Act: -0.1700
Data Index: 5729177 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.0975. Min Act: -0.1700
Data Index: 4967065 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.0350. Min Act: -0.1700
Data Index: 7681621 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0663. Min Range: -8.0663
Max Act: 7.0350. Min Act: -0.1700
Data Index: 5412803 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0663. Min Range: -8.0663
Max Act: 6.9725. Min Act: -0.1700
Data Index: 3579358 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0663. Min Range: -8.0663
Max Act: 6.9725. Min Act: -0.1700
Data Index: 2740046 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19