Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6326. Min Range: -7.6326
Max Act: 7.6326. Min Act: -0.1700
Data Index: 6014907 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6326. Min Range: -7.6326
Max Act: 7.2263. Min Act: -0.1700
Data Index: 8046267 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.9763. Min Act: -0.1700
Data Index: 6702148 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.9763. Min Act: -0.1700
Data Index: 2419652 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.9451. Min Act: -0.1700
Data Index: 8552875 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.8826. Min Act: -0.1700
Data Index: 8592639 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.8201. Min Act: -0.1700
Data Index: 5097520 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.7576. Min Act: -0.1700
Data Index: 6629568 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6951. Min Act: -0.1700
Data Index: 5694621 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6951. Min Act: -0.1700
Data Index: 1703499 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6326. Min Act: -0.1700
Data Index: 6087108 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6638. Min Act: -0.1700
Data Index: 5957720 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6326. Min Act: -0.1700
Data Index: 4141945 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6326. Min Act: -0.1700
Data Index: 4500957 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6326. Min Act: -0.1700
Data Index: 6200880 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6326. Min Act: -0.1700
Data Index: 7151038 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.6013. Min Act: -0.1700
Data Index: 4017939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.5701. Min Act: -0.1700
Data Index: 8366094 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.5388. Min Act: -0.1700
Data Index: 4363097 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6326. Min Range: -7.6326
Max Act: 6.5388. Min Act: -0.1700
Data Index: 2006009 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19