Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5485 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2524. Min Range: -8.2524
Max Act: 8.2524. Min Act: -0.1700
Data Index: 8554603 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2524. Min Range: -8.2524
Max Act: 8.2211. Min Act: -0.1700
Data Index: 5764720 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2524. Min Range: -8.2524
Max Act: 8.1274. Min Act: -0.1700
Data Index: 1104183 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.9399. Min Act: -0.1700
Data Index: 7558117 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.7211. Min Act: -0.1700
Data Index: 566040 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.6899. Min Act: -0.1700
Data Index: 7257941 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.6586. Min Act: -0.1700
Data Index: 3909799 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.6586. Min Act: -0.1700
Data Index: 2718655 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.6274. Min Act: -0.1700
Data Index: 7729294 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.6274. Min Act: -0.1700
Data Index: 7281208 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.6274. Min Act: -0.1700
Data Index: 6289730 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.5961. Min Act: -0.1700
Data Index: 4779959 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.5961. Min Act: -0.1700
Data Index: 431223 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.5024. Min Act: -0.1700
Data Index: 3398412 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.5024. Min Act: -0.1700
Data Index: 5772786 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.4711. Min Act: -0.1700
Data Index: 6627934 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.4399. Min Act: -0.1700
Data Index: 7181537 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.4086. Min Act: -0.1700
Data Index: 6214099 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.3774. Min Act: -0.1700
Data Index: 2261684 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2524. Min Range: -8.2524
Max Act: 7.4086. Min Act: -0.1700
Data Index: 3976182 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19