Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4676. Min Range: -6.4676
Max Act: 6.4676. Min Act: -0.1700
Data Index: 4604392 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.9676. Min Act: -0.1700
Data Index: 1715984 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.9676. Min Act: -0.1700
Data Index: 3996512 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.9676. Min Act: -0.1700
Data Index: 2651037 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.8426. Min Act: -0.1700
Data Index: 2402213 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.8113. Min Act: -0.1700
Data Index: 8364264 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5582245 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.8113. Min Act: -0.1700
Data Index: 6552300 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7801. Min Act: -0.1700
Data Index: 7074149 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7176. Min Act: -0.1700
Data Index: 75541 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7488. Min Act: -0.1700
Data Index: 2630230 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7488. Min Act: -0.1700
Data Index: 7417720 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7488. Min Act: -0.1700
Data Index: 149699 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7488. Min Act: -0.1700
Data Index: 1720292 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.7176. Min Act: -0.1700
Data Index: 3401445 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.6863. Min Act: -0.1700
Data Index: 1516486 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 6379632 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 5037200 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 2852907 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4676. Min Range: -6.4676
Max Act: 5.6863. Min Act: -0.1700
Data Index: 5821387 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19