Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1102 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.6619. Min Act: -0.1700
Data Index: 4324132 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.2244. Min Act: -0.1700
Data Index: 7448529 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.2244. Min Act: -0.1700
Data Index: 1324726 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.1619. Min Act: -0.1700
Data Index: 773585 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.1619. Min Act: -0.1700
Data Index: 4072557 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.1619. Min Act: -0.1700
Data Index: 5450065 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.0369. Min Act: -0.1700
Data Index: 1502230 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6619. Min Range: -8.6619
Max Act: 8.0369. Min Act: -0.1700
Data Index: 3722510 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.9744. Min Act: -0.1700
Data Index: 3982155 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.9119. Min Act: -0.1700
Data Index: 7921754 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.9744. Min Act: -0.1700
Data Index: 1074055 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.9119. Min Act: -0.1700
Data Index: 5718115 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.9119. Min Act: -0.1700
Data Index: 7277606 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.8494. Min Act: -0.1700
Data Index: 4100045 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.8494. Min Act: -0.1700
Data Index: 3121777 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.8494. Min Act: -0.1700
Data Index: 1679193 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.8494. Min Act: -0.1700
Data Index: 143524 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.8494. Min Act: -0.1700
Data Index: 8823180 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.8494. Min Act: -0.1700
Data Index: 2396553 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6619. Min Range: -8.6619
Max Act: 7.7869. Min Act: -0.1700
Data Index: 3575465 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19