Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.6255. Min Act: -0.1700
Data Index: 5248745 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.4067. Min Act: -0.1700
Data Index: 3753031 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.3442. Min Act: -0.1700
Data Index: 2155855 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.3130. Min Act: -0.1700
Data Index: 4357777 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.2505. Min Act: -0.1700
Data Index: 1084475 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.1255. Min Act: -0.1700
Data Index: 5101055 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.1255. Min Act: -0.1700
Data Index: 7488591 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0005. Min Act: -0.1700
Data Index: 7361977 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0005. Min Act: -0.1700
Data Index: 5290009 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.9692. Min Act: -0.1700
Data Index: 8614764 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.9692. Min Act: -0.1700
Data Index: 4185225 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.9380. Min Act: -0.1700
Data Index: 2863093 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.9380. Min Act: -0.1700
Data Index: 1092515 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.9380. Min Act: -0.1700
Data Index: 5671522 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.9380. Min Act: -0.1700
Data Index: 5813769 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.9067. Min Act: -0.1700
Data Index: 2555102 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.8755. Min Act: -0.1700
Data Index: 4996234 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.8755. Min Act: -0.1700
Data Index: 5078090 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.8755. Min Act: -0.1700
Data Index: 1273750 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6255. Min Range: -7.6255
Max Act: 6.8442. Min Act: -0.1700
Data Index: 2863981 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19