Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1754 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.3845. Min Act: -0.1700
Data Index: 7141835 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.3845. Min Act: -0.1700
Data Index: 1997655 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.2595. Min Act: -0.1700
Data Index: 5094454 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1970. Min Act: -0.1700
Data Index: 2108493 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1970. Min Act: -0.1700
Data Index: 6202400 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1657. Min Act: -0.1700
Data Index: 3703915 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1657. Min Act: -0.1700
Data Index: 1761982 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1657. Min Act: -0.1700
Data Index: 6202399 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1345. Min Act: -0.1700
Data Index: 4798476 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1032. Min Act: -0.1700
Data Index: 3355464 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1032. Min Act: -0.1700
Data Index: 5531796 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1345. Min Act: -0.1700
Data Index: 637065 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1032. Min Act: -0.1700
Data Index: 364650 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1032. Min Act: -0.1700
Data Index: 4768337 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1032. Min Act: -0.1700
Data Index: 8451171 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.1032. Min Act: -0.1700
Data Index: 4255946 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.0720. Min Act: -0.1700
Data Index: 1444983 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.0720. Min Act: -0.1700
Data Index: 3415044 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.0720. Min Act: -0.1700
Data Index: 5082062 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3845. Min Range: -4.3845
Max Act: 4.0407. Min Act: -0.1700
Data Index: 454571 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19