Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.4767. Min Act: -0.1700
Data Index: 1768259 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.3670. Min Act: -0.1700
Data Index: 6340029 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.3670. Min Act: -0.1700
Data Index: 816574 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.3199. Min Act: -0.1700
Data Index: 4461685 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.3042. Min Act: -0.1700
Data Index: 1447631 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.3042. Min Act: -0.1700
Data Index: 4591492 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.3042. Min Act: -0.1700
Data Index: 5988582 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2885. Min Act: -0.1700
Data Index: 3151738 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2728. Min Act: -0.1700
Data Index: 808353 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2571. Min Act: -0.1700
Data Index: 7403442 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2728. Min Act: -0.1700
Data Index: 1251395 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2728. Min Act: -0.1700
Data Index: 4402388 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2571. Min Act: -0.1700
Data Index: 1797100 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2256. Min Act: -0.1700
Data Index: 2172922 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2414. Min Act: -0.1700
Data Index: 4333777 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2414. Min Act: -0.1700
Data Index: 1395553 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2256. Min Act: -0.1700
Data Index: 5938883 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2099. Min Act: -0.1700
Data Index: 3664184 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.1942. Min Act: -0.1700
Data Index: 4148716 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4767. Min Range: -3.4767
Max Act: 3.2414. Min Act: -0.1700
Data Index: 6382937 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19