Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 471 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.5862. Min Act: -0.1700
Data Index: 7472821 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.4300. Min Act: -0.1700
Data Index: 1320128 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.3050. Min Act: -0.1700
Data Index: 7852224 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.3050. Min Act: -0.1700
Data Index: 5790093 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.1800. Min Act: -0.1700
Data Index: 5117880 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.1487. Min Act: -0.1700
Data Index: 2441278 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.1175. Min Act: -0.1700
Data Index: 576057 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.1175. Min Act: -0.1700
Data Index: 5380480 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.1175. Min Act: -0.1700
Data Index: 5431364 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.0550. Min Act: -0.1700
Data Index: 2441280 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.0237. Min Act: -0.1700
Data Index: 5000479 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5862. Min Range: -6.5862
Max Act: 6.0237. Min Act: -0.1700
Data Index: 2655270 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9925. Min Act: -0.1700
Data Index: 4101579 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9612. Min Act: -0.1700
Data Index: 7820754 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9925. Min Act: -0.1700
Data Index: 3273437 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9925. Min Act: -0.1700
Data Index: 1320127 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9925. Min Act: -0.1700
Data Index: 4572896 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9612. Min Act: -0.1700
Data Index: 2655264 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9612. Min Act: -0.1700
Data Index: 2220230 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5862. Min Range: -6.5862
Max Act: 5.9300. Min Act: -0.1700
Data Index: 6399553 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19