Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.7072. Min Act: -0.1700
Data Index: 727987 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.5822. Min Act: -0.1700
Data Index: 2783606 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.5197. Min Act: -0.1700
Data Index: 6361393 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.5197. Min Act: -0.1700
Data Index: 7875148 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.4885. Min Act: -0.1700
Data Index: 8672479 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.4885. Min Act: -0.1700
Data Index: 1584890 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.4572. Min Act: -0.1700
Data Index: 2117259 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.4260. Min Act: -0.1700
Data Index: 4665827 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.3635. Min Act: -0.1700
Data Index: 6781400 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.3322. Min Act: -0.1700
Data Index: 6572919 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.3010. Min Act: -0.1700
Data Index: 871553 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2697. Min Act: -0.1700
Data Index: 7174906 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2697. Min Act: -0.1700
Data Index: 4422365 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2697. Min Act: -0.1700
Data Index: 4143857 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2072. Min Act: -0.1700
Data Index: 363423 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2385. Min Act: -0.1700
Data Index: 6150564 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2385. Min Act: -0.1700
Data Index: 970290 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2072. Min Act: -0.1700
Data Index: 3035612 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2072. Min Act: -0.1700
Data Index: 2607142 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7072. Min Range: -4.7072
Max Act: 4.2072. Min Act: -0.1700
Data Index: 3161678 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19