Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1287 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.4242. Min Act: -0.1700
Data Index: 4818942 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3772. Min Act: -0.1700
Data Index: 4116498 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.4085. Min Act: -0.1700
Data Index: 6629908 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3772. Min Act: -0.1700
Data Index: 6125306 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3772. Min Act: -0.1700
Data Index: 3603408 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3615. Min Act: -0.1700
Data Index: 385100 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3772. Min Act: -0.1700
Data Index: 4204333 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3301. Min Act: -0.1700
Data Index: 3548988 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3301. Min Act: -0.1700
Data Index: 2614863 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3458. Min Act: -0.1700
Data Index: 8383718 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3615. Min Act: -0.1700
Data Index: 8704570 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3301. Min Act: -0.1700
Data Index: 8717601 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.2830. Min Act: -0.1700
Data Index: 1692489 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.2987. Min Act: -0.1700
Data Index: 1507112 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3144. Min Act: -0.1700
Data Index: 8292241 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3301. Min Act: -0.1700
Data Index: 4571136 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.2987. Min Act: -0.1700
Data Index: 3962114 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.3144. Min Act: -0.1700
Data Index: 4125033 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.2516. Min Act: -0.1700
Data Index: 5514179 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4242. Min Range: -3.4242
Max Act: 3.2830. Min Act: -0.1700
Data Index: 4813247 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19