Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.5307. Min Act: -0.1700
Data Index: 4189337 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.4370. Min Act: -0.1700
Data Index: 8052146 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.4682. Min Act: -0.1700
Data Index: 7604687 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.4057. Min Act: -0.1700
Data Index: 5034897 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.3745. Min Act: -0.1700
Data Index: 5564174 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.2807. Min Act: -0.1700
Data Index: 817186 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.2807. Min Act: -0.1700
Data Index: 3137174 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.2182. Min Act: -0.1700
Data Index: 5288061 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.2182. Min Act: -0.1700
Data Index: 8665202 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.1870. Min Act: -0.1700
Data Index: 926847 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.1557. Min Act: -0.1700
Data Index: 7010047 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.1245. Min Act: -0.1700
Data Index: 2117518 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.0932. Min Act: -0.1700
Data Index: 2484074 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.1245. Min Act: -0.1700
Data Index: 3271118 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.1245. Min Act: -0.1700
Data Index: 1326468 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.0620. Min Act: -0.1700
Data Index: 3271934 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.0932. Min Act: -0.1700
Data Index: 4902608 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.0932. Min Act: -0.1700
Data Index: 1332839 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.0932. Min Act: -0.1700
Data Index: 6835554 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5307. Min Range: -6.5307
Max Act: 6.0307. Min Act: -0.1700
Data Index: 7026236 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19