Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7510. Min Range: -9.7510
Max Act: 9.7510. Min Act: -0.1700
Data Index: 1168827 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7510. Min Range: -9.7510
Max Act: 9.6260. Min Act: -0.1700
Data Index: 5833222 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7510. Min Range: -9.7510
Max Act: 9.2510. Min Act: -0.1700
Data Index: 3606229 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.8760. Min Act: -0.1700
Data Index: 7107175 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.9385. Min Act: -0.1700
Data Index: 6138752 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.9385. Min Act: -0.1700
Data Index: 2629596 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.8760. Min Act: -0.1700
Data Index: 5718446 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.8760. Min Act: -0.1700
Data Index: 2310261 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.8760. Min Act: -0.1700
Data Index: 2539189 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.8135. Min Act: -0.1700
Data Index: 1089747 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.8135. Min Act: -0.1700
Data Index: 211004 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.7510. Min Act: -0.1700
Data Index: 6034085 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.7510. Min Act: -0.1700
Data Index: 7934484 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.6885. Min Act: -0.1700
Data Index: 7795356 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.6885. Min Act: -0.1700
Data Index: 7118246 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.5635. Min Act: -0.1700
Data Index: 5833221 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.6260. Min Act: -0.1700
Data Index: 4796764 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.6260. Min Act: -0.1700
Data Index: 3606228 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.5635. Min Act: -0.1700
Data Index: 5863503 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7510. Min Range: -9.7510
Max Act: 8.6260. Min Act: -0.1700
Data Index: 7428494 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19