Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5593 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.9257. Min Act: -0.1700
Data Index: 7430588 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.2694. Min Act: -0.1700
Data Index: 4134392 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.2069. Min Act: -0.1700
Data Index: 5871855 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.1757. Min Act: -0.1700
Data Index: 1498133 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.1444. Min Act: -0.1700
Data Index: 5683574 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.1132. Min Act: -0.1700
Data Index: 5174248 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.1132. Min Act: -0.1700
Data Index: 3867393 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0819. Min Act: -0.1700
Data Index: 229312 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0819. Min Act: -0.1700
Data Index: 7538610 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0819. Min Act: -0.1700
Data Index: 5999339 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0507. Min Act: -0.1700
Data Index: 1761281 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0507. Min Act: -0.1700
Data Index: 1499465 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0194. Min Act: -0.1700
Data Index: 1084060 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0194. Min Act: -0.1700
Data Index: 3737596 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9257. Min Range: -6.9257
Max Act: 5.9882. Min Act: -0.1700
Data Index: 1271825 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9257. Min Range: -6.9257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 2193558 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9257. Min Range: -6.9257
Max Act: 5.9882. Min Act: -0.1700
Data Index: 3463870 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9257. Min Range: -6.9257
Max Act: 6.0194. Min Act: -0.1700
Data Index: 1843166 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9257. Min Range: -6.9257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 2015065 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9257. Min Range: -6.9257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 483045 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19