Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2197 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3526. Min Range: -7.3526
Max Act: 7.3526. Min Act: -0.1700
Data Index: 2421670 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3526. Min Range: -7.3526
Max Act: 7.2589. Min Act: -0.1700
Data Index: 6329390 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3526. Min Range: -7.3526
Max Act: 7.1339. Min Act: -0.1700
Data Index: 7052608 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3526. Min Range: -7.3526
Max Act: 7.0714. Min Act: -0.1700
Data Index: 3857024 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3526. Min Range: -7.3526
Max Act: 7.0401. Min Act: -0.1700
Data Index: 4516094 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 782776 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3526. Min Range: -7.3526
Max Act: 7.0401. Min Act: -0.1700
Data Index: 3857021 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 8116566 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3526. Min Range: -7.3526
Max Act: 7.0089. Min Act: -0.1700
Data Index: 3922412 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 3857017 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 3857022 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 1519383 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 5907980 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 3857019 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9776. Min Act: -0.1700
Data Index: 3857020 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9464. Min Act: -0.1700
Data Index: 7085075 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9464. Min Act: -0.1700
Data Index: 3857029 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9151. Min Act: -0.1700
Data Index: 3857014 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9151. Min Act: -0.1700
Data Index: 3857016 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3526. Min Range: -7.3526
Max Act: 6.9151. Min Act: -0.1700
Data Index: 130907 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19