Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.2164. Min Act: -0.1700
Data Index: 4720039 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.1539. Min Act: -0.1700
Data Index: 3260029 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.1539. Min Act: -0.1700
Data Index: 7652761 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.1539. Min Act: -0.1700
Data Index: 3923423 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.1227. Min Act: -0.1700
Data Index: 5940623 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.0914. Min Act: -0.1700
Data Index: 1224949 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.0289. Min Act: -0.1700
Data Index: 4446040 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.0289. Min Act: -0.1700
Data Index: 1382173 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.0289. Min Act: -0.1700
Data Index: 6653330 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9976. Min Act: -0.1700
Data Index: 5542945 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2164. Min Range: -4.2164
Max Act: 4.0289. Min Act: -0.1700
Data Index: 8503710 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9664. Min Act: -0.1700
Data Index: 6175913 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9976. Min Act: -0.1700
Data Index: 3038137 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9664. Min Act: -0.1700
Data Index: 5119383 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9664. Min Act: -0.1700
Data Index: 8136538 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9664. Min Act: -0.1700
Data Index: 7577602 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9664. Min Act: -0.1700
Data Index: 5602254 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9664. Min Act: -0.1700
Data Index: 8106978 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9351. Min Act: -0.1700
Data Index: 7594090 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2164. Min Range: -4.2164
Max Act: 3.9351. Min Act: -0.1700
Data Index: 2822401 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19