Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.7126. Min Act: -0.1700
Data Index: 1979128 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.4935. Min Act: -0.1700
Data Index: 3716289 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.4622. Min Act: -0.1700
Data Index: 3519985 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.4308. Min Act: -0.1700
Data Index: 3322957 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.4152. Min Act: -0.1700
Data Index: 5152265 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.4308. Min Act: -0.1700
Data Index: 2583311 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.4152. Min Act: -0.1700
Data Index: 586206 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.4152. Min Act: -0.1700
Data Index: 4600523 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3995. Min Act: -0.1700
Data Index: 4098587 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3995. Min Act: -0.1700
Data Index: 745220 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3681. Min Act: -0.1700
Data Index: 1593337 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3368. Min Act: -0.1700
Data Index: 3299884 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3368. Min Act: -0.1700
Data Index: 946461 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3368. Min Act: -0.1700
Data Index: 8694568 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3211. Min Act: -0.1700
Data Index: 546417 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.3368. Min Act: -0.1700
Data Index: 2171472 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.2897. Min Act: -0.1700
Data Index: 563369 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.2897. Min Act: -0.1700
Data Index: 8513462 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.2897. Min Act: -0.1700
Data Index: 1824311 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7126. Min Range: -3.7126
Max Act: 3.2897. Min Act: -0.1700
Data Index: 7641410 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19