Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4366 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.6447. Min Act: -0.1700
Data Index: 5676567 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.4572. Min Act: -0.1700
Data Index: 1434402 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.4260. Min Act: -0.1700
Data Index: 6534368 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.4260. Min Act: -0.1700
Data Index: 157038 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.3947. Min Act: -0.1700
Data Index: 6203088 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.3947. Min Act: -0.1700
Data Index: 4450349 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.3010. Min Act: -0.1700
Data Index: 143970 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2697. Min Act: -0.1700
Data Index: 6071658 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2697. Min Act: -0.1700
Data Index: 8120298 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2385. Min Act: -0.1700
Data Index: 4129716 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2385. Min Act: -0.1700
Data Index: 3177203 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2385. Min Act: -0.1700
Data Index: 4637970 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2072. Min Act: -0.1700
Data Index: 6655652 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2072. Min Act: -0.1700
Data Index: 2339768 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.1760. Min Act: -0.1700
Data Index: 5796503 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2072. Min Act: -0.1700
Data Index: 8276566 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2072. Min Act: -0.1700
Data Index: 6753637 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.2072. Min Act: -0.1700
Data Index: 2643209 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.1760. Min Act: -0.1700
Data Index: 848312 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6447. Min Range: -5.6447
Max Act: 5.1760. Min Act: -0.1700
Data Index: 5329020 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19