Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1583. Min Range: -6.1583
Max Act: 6.1583. Min Act: -0.1700
Data Index: 8785353 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1583. Min Range: -6.1583
Max Act: 6.0020. Min Act: -0.1700
Data Index: 5524587 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.8458. Min Act: -0.1700
Data Index: 1930966 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.8458. Min Act: -0.1700
Data Index: 6383390 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.8145. Min Act: -0.1700
Data Index: 5313806 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.7520. Min Act: -0.1700
Data Index: 6982870 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.7520. Min Act: -0.1700
Data Index: 1067573 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6895. Min Act: -0.1700
Data Index: 2760180 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6895. Min Act: -0.1700
Data Index: 5835875 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6583. Min Act: -0.1700
Data Index: 775868 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6583. Min Act: -0.1700
Data Index: 6789467 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6583. Min Act: -0.1700
Data Index: 8601106 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6270. Min Act: -0.1700
Data Index: 4841350 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6270. Min Act: -0.1700
Data Index: 5901458 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3122344 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.5958. Min Act: -0.1700
Data Index: 4757641 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.5958. Min Act: -0.1700
Data Index: 5741283 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6270. Min Act: -0.1700
Data Index: 4586439 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.5958. Min Act: -0.1700
Data Index: 2393744 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1583. Min Range: -6.1583
Max Act: 5.6270. Min Act: -0.1700
Data Index: 3789742 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19