Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0520. Min Range: -2.0520
Max Act: 2.0520. Min Act: -0.1700
Data Index: 1130315 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0520. Min Range: -2.0520
Max Act: 2.0352. Min Act: -0.1700
Data Index: 6643547 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0520. Min Range: -2.0520
Max Act: 2.0520. Min Act: -0.1700
Data Index: 4078050 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0520. Min Range: -2.0520
Max Act: 2.0183. Min Act: -0.1700
Data Index: 7422819 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0520. Min Range: -2.0520
Max Act: 2.0014. Min Act: -0.1700
Data Index: 8657901 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9845. Min Act: -0.1700
Data Index: 2890694 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0520. Min Range: -2.0520
Max Act: 2.0014. Min Act: -0.1700
Data Index: 6798957 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0520. Min Range: -2.0520
Max Act: 2.0014. Min Act: -0.1700
Data Index: 4186639 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9845. Min Act: -0.1700
Data Index: 1380070 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9845. Min Act: -0.1700
Data Index: 45450 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9845. Min Act: -0.1700
Data Index: 4599871 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9676. Min Act: -0.1700
Data Index: 6451028 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9676. Min Act: -0.1700
Data Index: 4838919 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9506. Min Act: -0.1700
Data Index: 2458154 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9506. Min Act: -0.1700
Data Index: 3114468 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9676. Min Act: -0.1700
Data Index: 3991719 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9506. Min Act: -0.1700
Data Index: 3825166 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9506. Min Act: -0.1700
Data Index: 153578 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9506. Min Act: -0.1700
Data Index: 5319769 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0520. Min Range: -2.0520
Max Act: 1.9506. Min Act: -0.1700
Data Index: 5363780 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19