Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2089 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.2086. Min Act: -0.1700
Data Index: 5841155 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.2086. Min Act: -0.1700
Data Index: 2615781 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.1149. Min Act: -0.1700
Data Index: 48955 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.0836. Min Act: -0.1700
Data Index: 2925639 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.0836. Min Act: -0.1700
Data Index: 2174071 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.0211. Min Act: -0.1700
Data Index: 5311584 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.0211. Min Act: -0.1700
Data Index: 2505053 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.0211. Min Act: -0.1700
Data Index: 912804 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2086. Min Range: -5.2086
Max Act: 5.0211. Min Act: -0.1700
Data Index: 1041939 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9586. Min Act: -0.1700
Data Index: 6079693 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9899. Min Act: -0.1700
Data Index: 4969386 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9899. Min Act: -0.1700
Data Index: 3933965 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9899. Min Act: -0.1700
Data Index: 1570620 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9899. Min Act: -0.1700
Data Index: 2505041 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9586. Min Act: -0.1700
Data Index: 5161140 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4969401 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9274. Min Act: -0.1700
Data Index: 5311569 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9274. Min Act: -0.1700
Data Index: 105043 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9274. Min Act: -0.1700
Data Index: 5390111 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2086. Min Range: -5.2086
Max Act: 4.9274. Min Act: -0.1700
Data Index: 4121235 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19