Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.2268. Min Act: -0.1700
Data Index: 2519211 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.1956. Min Act: -0.1700
Data Index: 6169202 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.1643. Min Act: -0.1700
Data Index: 5599258 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.1331. Min Act: -0.1700
Data Index: 1387243 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.1018. Min Act: -0.1700
Data Index: 4696902 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.0706. Min Act: -0.1700
Data Index: 6396349 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.0706. Min Act: -0.1700
Data Index: 1110558 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.0081. Min Act: -0.1700
Data Index: 6985257 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2268. Min Range: -6.2268
Max Act: 6.0081. Min Act: -0.1700
Data Index: 6009978 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.9456. Min Act: -0.1700
Data Index: 362004 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.8206. Min Act: -0.1700
Data Index: 538465 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.7581. Min Act: -0.1700
Data Index: 58246 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.7893. Min Act: -0.1700
Data Index: 2992288 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.7581. Min Act: -0.1700
Data Index: 1069465 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.7581. Min Act: -0.1700
Data Index: 4285514 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.6956. Min Act: -0.1700
Data Index: 7844966 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.6956. Min Act: -0.1700
Data Index: 6268619 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.7268. Min Act: -0.1700
Data Index: 4306272 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.7581. Min Act: -0.1700
Data Index: 7116412 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2268. Min Range: -6.2268
Max Act: 5.6643. Min Act: -0.1700
Data Index: 870276 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19