Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.3869. Min Act: -0.1700
Data Index: 14405 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.3869. Min Act: -0.1700
Data Index: 5996081 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.2619. Min Act: -0.1700
Data Index: 5573937 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.2932. Min Act: -0.1700
Data Index: 1149086 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.2932. Min Act: -0.1700
Data Index: 31511 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.2619. Min Act: -0.1700
Data Index: 3379370 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.1994. Min Act: -0.1700
Data Index: 4148924 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.1682. Min Act: -0.1700
Data Index: 4248527 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.1057. Min Act: -0.1700
Data Index: 4639719 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.1057. Min Act: -0.1700
Data Index: 1163087 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.1057. Min Act: -0.1700
Data Index: 6913670 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0744. Min Act: -0.1700
Data Index: 2027483 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0744. Min Act: -0.1700
Data Index: 6911425 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5240036 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0744. Min Act: -0.1700
Data Index: 8512618 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0432. Min Act: -0.1700
Data Index: 646094 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0432. Min Act: -0.1700
Data Index: 1455121 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5222239 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0432. Min Act: -0.1700
Data Index: 5054020 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3869. Min Range: -6.3869
Max Act: 6.0119. Min Act: -0.1700
Data Index: 4702222 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19