Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.4721. Min Act: -0.1700
Data Index: 3523117 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.3471. Min Act: -0.1700
Data Index: 4787001 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.2846. Min Act: -0.1700
Data Index: 4008279 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.2221. Min Act: -0.1700
Data Index: 5236179 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.2221. Min Act: -0.1700
Data Index: 8700917 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.1596. Min Act: -0.1700
Data Index: 2798197 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.1596. Min Act: -0.1700
Data Index: 2515197 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.1596. Min Act: -0.1700
Data Index: 3537629 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.0971. Min Act: -0.1700
Data Index: 6222745 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4721. Min Range: -8.4721
Max Act: 8.0346. Min Act: -0.1700
Data Index: 832317 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.9096. Min Act: -0.1700
Data Index: 8438731 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.9096. Min Act: -0.1698
Data Index: 832320 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.9096. Min Act: -0.1700
Data Index: 832325 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.9096. Min Act: -0.1700
Data Index: 4964256 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.9096. Min Act: -0.1700
Data Index: 4419123 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.7846. Min Act: -0.1700
Data Index: 5867302 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.8471. Min Act: -0.1700
Data Index: 6568396 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.8471. Min Act: -0.1700
Data Index: 1517658 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.8471. Min Act: -0.1700
Data Index: 3686387 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4721. Min Range: -8.4721
Max Act: 7.8471. Min Act: -0.1700
Data Index: 6840584 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19