Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1934 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2153. Min Range: -8.2153
Max Act: 8.2153. Min Act: -0.1700
Data Index: 941846 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2153. Min Range: -8.2153
Max Act: 8.0278. Min Act: -0.1700
Data Index: 5918619 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.8403. Min Act: -0.1700
Data Index: 4228469 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.6528. Min Act: -0.1700
Data Index: 5072366 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.5903. Min Act: -0.1700
Data Index: 781716 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.5278. Min Act: -0.1700
Data Index: 5637788 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4965. Min Act: -0.1700
Data Index: 8224421 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4653. Min Act: -0.1700
Data Index: 3227747 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4653. Min Act: -0.1700
Data Index: 7300321 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4340. Min Act: -0.1700
Data Index: 3620549 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4340. Min Act: -0.1700
Data Index: 4296009 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4340. Min Act: -0.1700
Data Index: 8277805 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4340. Min Act: -0.1700
Data Index: 3183434 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4028. Min Act: -0.1700
Data Index: 3829231 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4028. Min Act: -0.1700
Data Index: 4193547 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4028. Min Act: -0.1700
Data Index: 277143 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.4028. Min Act: -0.1700
Data Index: 3113595 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.3715. Min Act: -0.1700
Data Index: 1283143 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.3715. Min Act: -0.1700
Data Index: 452642 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2153. Min Range: -8.2153
Max Act: 7.3403. Min Act: -0.1700
Data Index: 5968501 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19