Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 371 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.4655. Min Act: -0.1700
Data Index: 4513713 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.3405. Min Act: -0.1700
Data Index: 6082238 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.3405. Min Act: -0.1700
Data Index: 8377981 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.4030. Min Act: -0.1700
Data Index: 1559352 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.2155. Min Act: -0.1700
Data Index: 1573302 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.2155. Min Act: -0.1700
Data Index: 5646970 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.1530. Min Act: -0.1700
Data Index: 7506196 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.0905. Min Act: -0.1700
Data Index: 3874537 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4655. Min Range: -12.4655
Max Act: 12.0280. Min Act: -0.1700
Data Index: 1062695 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.9655. Min Act: -0.1700
Data Index: 3835944 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.9655. Min Act: -0.1700
Data Index: 2858519 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.9030. Min Act: -0.1700
Data Index: 4909543 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.9030. Min Act: -0.1700
Data Index: 4651157 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.9655. Min Act: -0.1700
Data Index: 5207953 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.8405. Min Act: -0.1700
Data Index: 2725284 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.8405. Min Act: -0.1700
Data Index: 7009671 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.8405. Min Act: -0.1700
Data Index: 5529378 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.8405. Min Act: -0.1700
Data Index: 6911022 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.7780. Min Act: -0.1700
Data Index: 5398205 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4655. Min Range: -12.4655
Max Act: 11.7780. Min Act: -0.1700
Data Index: 100208 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19