Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.8881. Min Act: -0.1700
Data Index: 3033858 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.7943. Min Act: -0.1700
Data Index: 2577415 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.7943. Min Act: -0.1700
Data Index: 7001547 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.7318. Min Act: -0.1700
Data Index: 8467492 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.7006. Min Act: -0.1700
Data Index: 6980608 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.7006. Min Act: -0.1700
Data Index: 7001572 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.6693. Min Act: -0.1700
Data Index: 6980606 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.6693. Min Act: -0.1700
Data Index: 7825890 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.6381. Min Act: -0.1700
Data Index: 2434671 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.6381. Min Act: -0.1700
Data Index: 3336703 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.6068. Min Act: -0.1700
Data Index: 671427 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.6381. Min Act: -0.1700
Data Index: 7045799 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.5443. Min Act: -0.1700
Data Index: 3901060 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.5131. Min Act: -0.1700
Data Index: 3798875 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.5131. Min Act: -0.1700
Data Index: 8335293 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.4818. Min Act: -0.1700
Data Index: 7912096 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.4818. Min Act: -0.1700
Data Index: 791892 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.4506. Min Act: -0.1700
Data Index: 6507289 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.4818. Min Act: -0.1700
Data Index: 3932693 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8881. Min Range: -5.8881
Max Act: 5.4506. Min Act: -0.1700
Data Index: 5250089 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19