Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2240 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.8583. Min Act: -0.1700
Data Index: 7164936 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.7958. Min Act: -0.1700
Data Index: 3524931 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6708. Min Act: -0.1700
Data Index: 7993292 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6395. Min Act: -0.1700
Data Index: 4359041 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6395. Min Act: -0.1700
Data Index: 1256450 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6395. Min Act: -0.1700
Data Index: 2976251 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6083. Min Act: -0.1700
Data Index: 7773825 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5770. Min Act: -0.1700
Data Index: 4432826 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5770. Min Act: -0.1700
Data Index: 8197310 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5770. Min Act: -0.1700
Data Index: 4831873 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5458. Min Act: -0.1700
Data Index: 3097510 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.4833. Min Act: -0.1700
Data Index: 4550643 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5145. Min Act: -0.1700
Data Index: 6725637 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5145. Min Act: -0.1700
Data Index: 2588062 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5145. Min Act: -0.1700
Data Index: 2785194 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5145. Min Act: -0.1700
Data Index: 380042 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5145. Min Act: -0.1700
Data Index: 7727491 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.4833. Min Act: -0.1700
Data Index: 1810096 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.4833. Min Act: -0.1700
Data Index: 6656797 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.4833. Min Act: -0.1700
Data Index: 2233689 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19