Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.4562. Min Act: -0.1700
Data Index: 8439702 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.3312. Min Act: -0.1700
Data Index: 3106259 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.2687. Min Act: -0.1700
Data Index: 3048220 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.2374. Min Act: -0.1700
Data Index: 864401 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.2374. Min Act: -0.1699
Data Index: 4650958 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.2687. Min Act: -0.1700
Data Index: 756021 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.2062. Min Act: -0.1700
Data Index: 5600317 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.1437. Min Act: -0.1700
Data Index: 728408 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.1749. Min Act: -0.1700
Data Index: 3718542 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0812. Min Act: -0.1700
Data Index: 6339906 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.1124. Min Act: -0.1700
Data Index: 3257484 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0812. Min Act: -0.1700
Data Index: 5686674 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0812. Min Act: -0.1700
Data Index: 1821289 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.1124. Min Act: -0.1700
Data Index: 370060 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0499. Min Act: -0.1700
Data Index: 1708671 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0499. Min Act: -0.1700
Data Index: 8686514 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0187. Min Act: -0.1700
Data Index: 7290687 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0499. Min Act: -0.1700
Data Index: 7377257 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0187. Min Act: -0.1700
Data Index: 6381334 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4562. Min Range: -5.4562
Max Act: 5.0187. Min Act: -0.1700
Data Index: 8552147 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19