Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1984. Min Range: -7.1984
Max Act: 7.1984. Min Act: -0.1700
Data Index: 6954712 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.7922. Min Act: -0.1700
Data Index: 1410602 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.5734. Min Act: -0.1700
Data Index: 4015754 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.5109. Min Act: -0.1700
Data Index: 7818539 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.3859. Min Act: -0.1700
Data Index: 4692481 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.3547. Min Act: -0.1700
Data Index: 1902612 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.3547. Min Act: -0.1700
Data Index: 2205335 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.3547. Min Act: -0.1700
Data Index: 1050187 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.3547. Min Act: -0.1700
Data Index: 5455139 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.3234. Min Act: -0.1700
Data Index: 4755370 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.2922. Min Act: -0.1700
Data Index: 4357634 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.2922. Min Act: -0.1700
Data Index: 6309793 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.2297. Min Act: -0.1700
Data Index: 8312416 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.2297. Min Act: -0.1700
Data Index: 5085289 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.2297. Min Act: -0.1700
Data Index: 5824232 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.1984. Min Act: -0.1700
Data Index: 216310 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.1984. Min Act: -0.1700
Data Index: 8345710 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.1984. Min Act: -0.1700
Data Index: 748385 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.1359. Min Act: -0.1700
Data Index: 3876743 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1984. Min Range: -7.1984
Max Act: 6.1672. Min Act: -0.1700
Data Index: 8070762 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19