Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 845 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.8478. Min Act: -0.1700
Data Index: 5489752 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.8478. Min Act: -0.1700
Data Index: 7594381 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.7540. Min Act: -0.1700
Data Index: 4293344 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.5978. Min Act: -0.1700
Data Index: 1696239 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.5040. Min Act: -0.1700
Data Index: 3207412 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.5040. Min Act: -0.1700
Data Index: 8664261 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.4728. Min Act: -0.1700
Data Index: 2170698 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.4728. Min Act: -0.1700
Data Index: 5716602 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.4415. Min Act: -0.1700
Data Index: 3078552 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.4103. Min Act: -0.1700
Data Index: 4949892 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.4103. Min Act: -0.1700
Data Index: 1480273 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.4103. Min Act: -0.1700
Data Index: 7736311 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.4103. Min Act: -0.1700
Data Index: 3590063 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.3790. Min Act: -0.1700
Data Index: 701780 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.3790. Min Act: -0.1700
Data Index: 2049071 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.3478. Min Act: -0.1700
Data Index: 3746946 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.3478. Min Act: -0.1700
Data Index: 6840494 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.3165. Min Act: -0.1700
Data Index: 7083004 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.3478. Min Act: -0.1700
Data Index: 7203700 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8478. Min Range: -4.8478
Max Act: 4.3478. Min Act: -0.1700
Data Index: 5044788 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19