Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.2503. Min Act: -0.1700
Data Index: 3448484 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.2191. Min Act: -0.1700
Data Index: 3350463 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.2816. Min Act: -0.1700
Data Index: 8135506 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1566. Min Act: -0.1700
Data Index: 2545088 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1878. Min Act: -0.1700
Data Index: 3519572 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1878. Min Act: -0.1700
Data Index: 6817694 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1566. Min Act: -0.1700
Data Index: 1123916 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1566. Min Act: -0.1700
Data Index: 4848755 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1253. Min Act: -0.1700
Data Index: 1600962 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1253. Min Act: -0.1700
Data Index: 5393857 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1253. Min Act: -0.1700
Data Index: 2629083 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0628. Min Act: -0.1700
Data Index: 2653382 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1253. Min Act: -0.1700
Data Index: 8098949 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0941. Min Act: -0.1700
Data Index: 8518784 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0628. Min Act: -0.1700
Data Index: 5199604 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1566. Min Act: -0.1700
Data Index: 6735032 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0941. Min Act: -0.1700
Data Index: 8672903 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0941. Min Act: -0.1700
Data Index: 1796162 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0941. Min Act: -0.1700
Data Index: 5171669 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0316. Min Act: -0.1700
Data Index: 6552887 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19