Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 743 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0734. Min Range: -4.0734
Max Act: 4.0734. Min Act: -0.1700
Data Index: 5747089 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.9171. Min Act: -0.1700
Data Index: 419278 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7920. Min Act: -0.1700
Data Index: 1587736 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.8233. Min Act: -0.1700
Data Index: 5383552 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 6693382 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7920. Min Act: -0.1700
Data Index: 4215706 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 4348597 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 2717065 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 6023479 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7294. Min Act: -0.1700
Data Index: 789920 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 1494264 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 3633011 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 6451468 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 95371 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 1289051 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 5055317 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7138. Min Act: -0.1700
Data Index: 918016 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7294. Min Act: -0.1700
Data Index: 1804613 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7607. Min Act: -0.1700
Data Index: 3052390 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0734. Min Range: -4.0734
Max Act: 3.7138. Min Act: -0.1700
Data Index: 3788361 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19