Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.6616. Min Act: -0.1700
Data Index: 6535317 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.6303. Min Act: -0.1700
Data Index: 5330637 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.5991. Min Act: -0.1700
Data Index: 5188212 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.5678. Min Act: -0.1700
Data Index: 2231731 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.5366. Min Act: -0.1700
Data Index: 1079592 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.5366. Min Act: -0.1700
Data Index: 5857053 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.5366. Min Act: -0.1700
Data Index: 1341175 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.5053. Min Act: -0.1700
Data Index: 8505153 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.5053. Min Act: -0.1700
Data Index: 992483 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.4741. Min Act: -0.1700
Data Index: 8135225 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.4116. Min Act: -0.1700
Data Index: 968636 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.3803. Min Act: -0.1700
Data Index: 2006938 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.4116. Min Act: -0.1700
Data Index: 3941858 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.4116. Min Act: -0.1700
Data Index: 1467047 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.4116. Min Act: -0.1700
Data Index: 3658928 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.4116. Min Act: -0.1700
Data Index: 7520081 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.3803. Min Act: -0.1700
Data Index: 4172823 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.3803. Min Act: -0.1700
Data Index: 3217506 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.3803. Min Act: -0.1700
Data Index: 3545005 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6616. Min Range: -6.6616
Max Act: 6.3803. Min Act: -0.1700
Data Index: 2399087 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19