Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.7021. Min Act: -0.1700
Data Index: 295544 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.6396. Min Act: -0.1700
Data Index: 7218872 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.5771. Min Act: -0.1700
Data Index: 47187 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.5771. Min Act: -0.1700
Data Index: 872922 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.3271. Min Act: -0.1700
Data Index: 6316869 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.3271. Min Act: -0.1700
Data Index: 2165549 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.3271. Min Act: -0.1700
Data Index: 1332046 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.2021. Min Act: -0.1700
Data Index: 6794581 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.2021. Min Act: -0.1700
Data Index: 2935275 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.2021. Min Act: -0.1700
Data Index: 2028044 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.2021. Min Act: -0.1700
Data Index: 892253 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.1396. Min Act: -0.1700
Data Index: 3920074 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.1396. Min Act: -0.1700
Data Index: 3682061 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.1396. Min Act: -0.1700
Data Index: 2591136 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.1396. Min Act: -0.1700
Data Index: 8697154 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.1396. Min Act: -0.1700
Data Index: 8570705 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.0771. Min Act: -0.1700
Data Index: 2704914 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.1396. Min Act: -0.1700
Data Index: 3475839 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.0771. Min Act: -0.1700
Data Index: 6913860 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7021. Min Range: -9.7021
Max Act: 9.0771. Min Act: -0.1700
Data Index: 2924621 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19