Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4518 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0827. Min Range: -9.0827
Max Act: 9.0202. Min Act: -0.1700
Data Index: 1922913 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0827. Min Range: -9.0827
Max Act: 9.0827. Min Act: -0.1700
Data Index: 3761633 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0827. Min Range: -9.0827
Max Act: 9.0827. Min Act: -0.1700
Data Index: 294431 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0827. Min Range: -9.0827
Max Act: 9.0202. Min Act: -0.1700
Data Index: 1800422 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.9577. Min Act: -0.1700
Data Index: 6735429 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.8327. Min Act: -0.1700
Data Index: 6131066 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.7077. Min Act: -0.1700
Data Index: 234570 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.4577. Min Act: -0.1700
Data Index: 787472 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.3952. Min Act: -0.1700
Data Index: 2316360 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.3952. Min Act: -0.1700
Data Index: 1557524 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.3327. Min Act: -0.1700
Data Index: 3412955 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.3327. Min Act: -0.1700
Data Index: 352576 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.3327. Min Act: -0.1700
Data Index: 8343190 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.3327. Min Act: -0.1700
Data Index: 3833469 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.3327. Min Act: -0.1700
Data Index: 2884055 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.2702. Min Act: -0.1700
Data Index: 5604842 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.2702. Min Act: -0.1700
Data Index: 5718708 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.2077. Min Act: -0.1700
Data Index: 6304146 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.2702. Min Act: -0.1700
Data Index: 2153564 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0827. Min Range: -9.0827
Max Act: 8.2702. Min Act: -0.1700
Data Index: 2418652 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19