Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.5630. Min Act: -0.1700
Data Index: 4587505 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.3130. Min Act: -0.1700
Data Index: 3608009 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.2505. Min Act: -0.1700
Data Index: 8175245 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.1880. Min Act: -0.1700
Data Index: 8195588 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.1880. Min Act: -0.1700
Data Index: 5012235 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.1255. Min Act: -0.1700
Data Index: 6587705 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.1255. Min Act: -0.1700
Data Index: 658810 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.0005. Min Act: -0.1700
Data Index: 547257 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.0630. Min Act: -0.1700
Data Index: 5497983 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.0630. Min Act: -0.1700
Data Index: 2295533 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.0630. Min Act: -0.1700
Data Index: 6220746 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5630. Min Range: -8.5630
Max Act: 7.9380. Min Act: -0.1700
Data Index: 6716641 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.0005. Min Act: -0.1700
Data Index: 4900035 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.0005. Min Act: -0.1700
Data Index: 5562609 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5630. Min Range: -8.5630
Max Act: 8.0005. Min Act: -0.1700
Data Index: 6739587 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5630. Min Range: -8.5630
Max Act: 7.9380. Min Act: -0.1700
Data Index: 988529 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5630. Min Range: -8.5630
Max Act: 7.9380. Min Act: -0.1700
Data Index: 4044632 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5630. Min Range: -8.5630
Max Act: 7.9380. Min Act: -0.1700
Data Index: 3140048 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5630. Min Range: -8.5630
Max Act: 7.9380. Min Act: -0.1700
Data Index: 1567330 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5630. Min Range: -8.5630
Max Act: 7.8755. Min Act: -0.1700
Data Index: 6312 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19