Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.7510. Min Act: -0.1700
Data Index: 7240131 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.7353. Min Act: -0.1700
Data Index: 1951251 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.7353. Min Act: -0.1700
Data Index: 2218227 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6884. Min Act: -0.1700
Data Index: 5083786 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6728. Min Act: -0.1700
Data Index: 2263069 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6571. Min Act: -0.1700
Data Index: 366387 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6415. Min Act: -0.1700
Data Index: 1913789 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6415. Min Act: -0.1700
Data Index: 8519518 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6102. Min Act: -0.1700
Data Index: 4692850 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6415. Min Act: -0.1700
Data Index: 4971055 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6258. Min Act: -0.1700
Data Index: 6866152 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.6102. Min Act: -0.1700
Data Index: 4327949 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5789. Min Act: -0.1700
Data Index: 1880775 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5789. Min Act: -0.1700
Data Index: 3948403 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5632. Min Act: -0.1700
Data Index: 6141163 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5632. Min Act: -0.1700
Data Index: 2801216 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5632. Min Act: -0.1700
Data Index: 1829516 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5632. Min Act: -0.1700
Data Index: 8361852 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5162. Min Act: -0.1700
Data Index: 1007957 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7510. Min Range: -3.7510
Max Act: 3.5476. Min Act: -0.1700
Data Index: 3064521 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19