Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 451 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.3370. Min Act: -0.1700
Data Index: 4948344 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.3058. Min Act: -0.1700
Data Index: 8243759 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.3058. Min Act: -0.1700
Data Index: 2617459 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.2433. Min Act: -0.1700
Data Index: 3543941 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.2433. Min Act: -0.1700
Data Index: 7661903 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.2120. Min Act: -0.1700
Data Index: 6253085 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.2120. Min Act: -0.1700
Data Index: 5735994 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1808. Min Act: -0.1700
Data Index: 8669332 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1808. Min Act: -0.1700
Data Index: 5735993 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1495. Min Act: -0.1700
Data Index: 2126176 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 2050376 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0870. Min Act: -0.1700
Data Index: 6997821 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 5735998 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 8300001 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 4578892 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 5735987 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 4986690 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 8299987 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1183. Min Act: -0.1700
Data Index: 473985 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0870. Min Act: -0.1700
Data Index: 2446473 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19