Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 529 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.8552. Min Act: -0.1700
Data Index: 3192584 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.8295. Min Act: -0.1700
Data Index: 7584783 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.8209. Min Act: -0.1700
Data Index: 7720859 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.8037. Min Act: -0.1700
Data Index: 3871964 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.8123. Min Act: -0.1700
Data Index: 8534513 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7951. Min Act: -0.1700
Data Index: 6406546 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7779. Min Act: -0.1700
Data Index: 1474180 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7693. Min Act: -0.1700
Data Index: 3220574 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7607. Min Act: -0.1700
Data Index: 5105685 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7520. Min Act: -0.1700
Data Index: 1937774 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7607. Min Act: -0.1699
Data Index: 2483897 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7434. Min Act: -0.1700
Data Index: 1937773 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7434. Min Act: -0.1700
Data Index: 6294512 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7434. Min Act: -0.1700
Data Index: 4553361 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7520. Min Act: -0.1700
Data Index: 689743 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7261. Min Act: -0.1700
Data Index: 7668468 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7174. Min Act: -0.1700
Data Index: 968594 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7261. Min Act: -0.1700
Data Index: 5827867 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7174. Min Act: -0.1700
Data Index: 5354671 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8552. Min Range: -1.8552
Max Act: 1.7088. Min Act: -0.1700
Data Index: 3909583 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19