Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4982 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.9113. Min Act: -0.1700
Data Index: 7267363 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.7550. Min Act: -0.1700
Data Index: 8183161 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.7550. Min Act: -0.1700
Data Index: 6250708 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.7237. Min Act: -0.1700
Data Index: 116869 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.7237. Min Act: -0.1700
Data Index: 2814224 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.6924. Min Act: -0.1700
Data Index: 5002162 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.6924. Min Act: -0.1700
Data Index: 7985694 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.6611. Min Act: -0.1700
Data Index: 3813633 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.6611. Min Act: -0.1700
Data Index: 5270258 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.6611. Min Act: -0.1700
Data Index: 67345 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.6298. Min Act: -0.1700
Data Index: 6236340 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5985. Min Act: -0.1700
Data Index: 5192177 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5985. Min Act: -0.1700
Data Index: 116870 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5672. Min Act: -0.1700
Data Index: 836848 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5672. Min Act: -0.1700
Data Index: 8729881 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5359. Min Act: -0.1700
Data Index: 2848870 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5359. Min Act: -0.1700
Data Index: 8716475 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.4733. Min Act: -0.1700
Data Index: 2132053 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5046. Min Act: -0.1700
Data Index: 3413498 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9113. Min Range: -3.9113
Max Act: 3.5046. Min Act: -0.1700
Data Index: 449501 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19