Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3439. Min Range: -5.3439
Max Act: 5.3439. Min Act: -0.1700
Data Index: 126971 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3439. Min Range: -5.3439
Max Act: 5.3127. Min Act: -0.1700
Data Index: 1381174 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3439. Min Range: -5.3439
Max Act: 5.3127. Min Act: -0.1700
Data Index: 8446043 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3439. Min Range: -5.3439
Max Act: 5.0627. Min Act: -0.1700
Data Index: 2616215 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.9689. Min Act: -0.1700
Data Index: 5009692 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.9377. Min Act: -0.1700
Data Index: 7721920 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.9377. Min Act: -0.1700
Data Index: 3112159 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.9064. Min Act: -0.1700
Data Index: 4392326 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.9064. Min Act: -0.1700
Data Index: 6109598 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8752. Min Act: -0.1700
Data Index: 2393328 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8752. Min Act: -0.1700
Data Index: 2536442 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8439. Min Act: -0.1700
Data Index: 6921648 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8439. Min Act: -0.1700
Data Index: 4490399 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8127. Min Act: -0.1700
Data Index: 6192594 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8439. Min Act: -0.1700
Data Index: 5687764 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8127. Min Act: -0.1700
Data Index: 24174 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8127. Min Act: -0.1700
Data Index: 832012 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8127. Min Act: -0.1700
Data Index: 6357679 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8127. Min Act: -0.1700
Data Index: 5566120 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3439. Min Range: -5.3439
Max Act: 4.8127. Min Act: -0.1700
Data Index: 5111837 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19