Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 92 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4512. Min Act: -0.1700
Data Index: 813257 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3040. Min Act: -0.1700
Data Index: 2128903 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.2711. Min Act: -0.1700
Data Index: 6323153 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.2546. Min Act: -0.1700
Data Index: 8019807 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.2215. Min Act: -0.1700
Data Index: 6506895 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.2215. Min Act: -0.1700
Data Index: 3993120 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.2049. Min Act: -0.1700
Data Index: 6007786 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.2049. Min Act: -0.1700
Data Index: 560014 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1551. Min Act: -0.1700
Data Index: 5904574 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1384. Min Act: -0.1700
Data Index: 1012633 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1717. Min Act: -0.1700
Data Index: 7707637 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1883. Min Act: -0.1700
Data Index: 6007784 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1384. Min Act: -0.1700
Data Index: 3786084 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1551. Min Act: -0.1700
Data Index: 2217573 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1883. Min Act: -0.1700
Data Index: 3071895 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1717. Min Act: -0.1700
Data Index: 3101402 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1717. Min Act: -0.1700
Data Index: 1426779 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1717. Min Act: -0.1700
Data Index: 5768601 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1217. Min Act: -0.1700
Data Index: 4896116 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.1217. Min Act: -0.1700
Data Index: 7940189 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19