Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3270 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3261. Min Range: -10.3261
Max Act: 10.3261. Min Act: -0.1700
Data Index: 4236371 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3261. Min Range: -10.3261
Max Act: 10.1386. Min Act: -0.1700
Data Index: 4818796 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3261. Min Range: -10.3261
Max Act: 10.0761. Min Act: -0.1700
Data Index: 1008792 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3261. Min Range: -10.3261
Max Act: 10.0761. Min Act: -0.1700
Data Index: 6273405 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3261. Min Range: -10.3261
Max Act: 10.0136. Min Act: -0.1700
Data Index: 8060032 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3261. Min Range: -10.3261
Max Act: 10.0761. Min Act: -0.1700
Data Index: 449216 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.9511. Min Act: -0.1700
Data Index: 2545157 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.8886. Min Act: -0.1700
Data Index: 2015403 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7636. Min Act: -0.1700
Data Index: 1039976 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7636. Min Act: -0.1700
Data Index: 7363725 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7636. Min Act: -0.1700
Data Index: 2489799 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7636. Min Act: -0.1700
Data Index: 6061122 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7636. Min Act: -0.1700
Data Index: 1039975 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7011. Min Act: -0.1700
Data Index: 5636497 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7636. Min Act: -0.1700
Data Index: 1006658 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.7011. Min Act: -0.1700
Data Index: 4499965 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.6386. Min Act: -0.1700
Data Index: 6317198 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.6386. Min Act: -0.1700
Data Index: 6273403 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.5761. Min Act: -0.1700
Data Index: 3673244 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3261. Min Range: -10.3261
Max Act: 9.5761. Min Act: -0.1700
Data Index: 1361507 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19