Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5553 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.6687. Min Act: -0.1700
Data Index: 8084234 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.6374. Min Act: -0.1700
Data Index: 8425133 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.6061. Min Act: -0.1700
Data Index: 7060870 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5748. Min Act: -0.1700
Data Index: 5514112 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5748. Min Act: -0.1700
Data Index: 7387307 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5435. Min Act: -0.1700
Data Index: 5545963 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5748. Min Act: -0.1700
Data Index: 260704 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5435. Min Act: -0.1700
Data Index: 8804154 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5122. Min Act: -0.1700
Data Index: 3607276 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5122. Min Act: -0.1700
Data Index: 946174 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5122. Min Act: -0.1700
Data Index: 853591 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.4808. Min Act: -0.1700
Data Index: 6261903 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5122. Min Act: -0.1700
Data Index: 152527 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5122. Min Act: -0.1700
Data Index: 2601299 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.5122. Min Act: -0.1700
Data Index: 2172184 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.4808. Min Act: -0.1700
Data Index: 2397728 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.4808. Min Act: -0.1700
Data Index: 5110068 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.4808. Min Act: -0.1700
Data Index: 3855977 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.4808. Min Act: -0.1700
Data Index: 6933350 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6687. Min Range: -3.6687
Max Act: 3.4808. Min Act: -0.1700
Data Index: 7137763 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19