Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2553. Min Range: -7.2553
Max Act: 7.2553. Min Act: -0.1700
Data Index: 887519 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2553. Min Range: -7.2553
Max Act: 7.0365. Min Act: -0.1700
Data Index: 5047135 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.9740. Min Act: -0.1700
Data Index: 5520016 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.9115. Min Act: -0.1700
Data Index: 1853942 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.9115. Min Act: -0.1700
Data Index: 6065474 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.8803. Min Act: -0.1700
Data Index: 4690461 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.7240. Min Act: -0.1700
Data Index: 3233464 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.7240. Min Act: -0.1700
Data Index: 7792542 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.6615. Min Act: -0.1700
Data Index: 3052945 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.6303. Min Act: -0.1700
Data Index: 710356 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.6928. Min Act: -0.1700
Data Index: 8175579 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.6303. Min Act: -0.1700
Data Index: 6524012 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.6303. Min Act: -0.1700
Data Index: 7216945 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.5678. Min Act: -0.1700
Data Index: 3137068 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.5678. Min Act: -0.1700
Data Index: 7461057 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.5365. Min Act: -0.1700
Data Index: 1944869 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.5365. Min Act: -0.1700
Data Index: 2273778 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.5053. Min Act: -0.1700
Data Index: 1261893 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4048164 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2553. Min Range: -7.2553
Max Act: 6.4740. Min Act: -0.1700
Data Index: 2175369 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19