Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1308 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.4944. Min Act: -0.1700
Data Index: 3988815 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.4631. Min Act: -0.1700
Data Index: 3597326 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.4631. Min Act: -0.1700
Data Index: 3009359 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.4006. Min Act: -0.1700
Data Index: 2767242 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.3694. Min Act: -0.1700
Data Index: 2166959 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.3381. Min Act: -0.1700
Data Index: 4316846 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.2756. Min Act: -0.1700
Data Index: 4316845 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.2444. Min Act: -0.1700
Data Index: 6414994 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.2131. Min Act: -0.1700
Data Index: 100247 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.2444. Min Act: -0.1700
Data Index: 2817286 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.2131. Min Act: -0.1700
Data Index: 2600264 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1819. Min Act: -0.1700
Data Index: 3658223 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1819. Min Act: -0.1700
Data Index: 5495150 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1819. Min Act: -0.1700
Data Index: 4717939 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1506. Min Act: -0.1700
Data Index: 8407911 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1506. Min Act: -0.1700
Data Index: 8718469 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1506. Min Act: -0.1700
Data Index: 1708595 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1506. Min Act: -0.1700
Data Index: 7650126 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1819. Min Act: -0.1700
Data Index: 8061782 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4944. Min Range: -4.4944
Max Act: 4.1194. Min Act: -0.1700
Data Index: 7524626 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19