Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4740. Min Range: -8.4740
Max Act: 8.4740. Min Act: -0.1700
Data Index: 7685227 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4740. Min Range: -8.4740
Max Act: 8.2865. Min Act: -0.1700
Data Index: 6338819 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4740. Min Range: -8.4740
Max Act: 8.0990. Min Act: -0.1700
Data Index: 7966003 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4740. Min Range: -8.4740
Max Act: 8.0365. Min Act: -0.1700
Data Index: 5928749 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4740. Min Range: -8.4740
Max Act: 8.0990. Min Act: -0.1700
Data Index: 1773861 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4740. Min Range: -8.4740
Max Act: 8.0365. Min Act: -0.1700
Data Index: 8455341 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.9740. Min Act: -0.1700
Data Index: 7766373 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.9115. Min Act: -0.1700
Data Index: 5452402 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.9115. Min Act: -0.1700
Data Index: 6144738 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.8803. Min Act: -0.1700
Data Index: 855718 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.9115. Min Act: -0.1700
Data Index: 2491032 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.8490. Min Act: -0.1700
Data Index: 6845592 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.7865. Min Act: -0.1700
Data Index: 6122801 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.7865. Min Act: -0.1700
Data Index: 1240462 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.7553. Min Act: -0.1700
Data Index: 5646743 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.7553. Min Act: -0.1700
Data Index: 1709182 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.7240. Min Act: -0.1700
Data Index: 2434676 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.6615. Min Act: -0.1700
Data Index: 7925295 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.6615. Min Act: -0.1700
Data Index: 2679713 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4740. Min Range: -8.4740
Max Act: 7.6928. Min Act: -0.1700
Data Index: 4943841 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19