Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.6750. Min Act: -0.1700
Data Index: 1988974 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.6438. Min Act: -0.1700
Data Index: 8676530 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.6125. Min Act: -0.1700
Data Index: 310181 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.5500. Min Act: -0.1700
Data Index: 811304 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.5188. Min Act: -0.1700
Data Index: 8809294 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.5188. Min Act: -0.1700
Data Index: 4449964 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3977616 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.4875. Min Act: -0.1700
Data Index: 811305 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.4563. Min Act: -0.1700
Data Index: 4030669 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.4250. Min Act: -0.1700
Data Index: 557130 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.4250. Min Act: -0.1700
Data Index: 7701975 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3625. Min Act: -0.1700
Data Index: 2926206 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3938. Min Act: -0.1700
Data Index: 4109191 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3938. Min Act: -0.1700
Data Index: 2530962 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3313. Min Act: -0.1700
Data Index: 4154199 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3313. Min Act: -0.1700
Data Index: 4890109 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3313. Min Act: -0.1700
Data Index: 8747070 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3313. Min Act: -0.1700
Data Index: 576005 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3313. Min Act: -0.1700
Data Index: 1688185 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6750. Min Range: -5.6750
Max Act: 5.3000. Min Act: -0.1700
Data Index: 4761860 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19