Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.8561. Min Act: -0.1700
Data Index: 8513367 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.7624. Min Act: -0.1700
Data Index: 3868574 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.4811. Min Act: -0.1700
Data Index: 155108 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.4499. Min Act: -0.1700
Data Index: 6470785 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.3561. Min Act: -0.1700
Data Index: 7234756 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.3249. Min Act: -0.1700
Data Index: 6984939 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.2936. Min Act: -0.1700
Data Index: 5943749 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.2624. Min Act: -0.1700
Data Index: 3933392 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.2311. Min Act: -0.1700
Data Index: 6987891 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.2311. Min Act: -0.1700
Data Index: 3064701 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.1374. Min Act: -0.1700
Data Index: 8594721 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.1374. Min Act: -0.1700
Data Index: 7149035 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.1374. Min Act: -0.1700
Data Index: 8709501 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.1061. Min Act: -0.1700
Data Index: 841425 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.0749. Min Act: -0.1700
Data Index: 168697 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8561. Min Range: -6.8561
Max Act: 5.9811. Min Act: -0.1700
Data Index: 5775034 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8561. Min Range: -6.8561
Max Act: 6.0436. Min Act: -0.1700
Data Index: 8338937 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8561. Min Range: -6.8561
Max Act: 5.9811. Min Act: -0.1700
Data Index: 128237 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8561. Min Range: -6.8561
Max Act: 5.9811. Min Act: -0.1700
Data Index: 4612310 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8561. Min Range: -6.8561
Max Act: 5.9499. Min Act: -0.1700
Data Index: 641589 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19