Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.9909. Min Act: -0.1700
Data Index: 4317856 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.9909. Min Act: -0.1700
Data Index: 7839543 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.6159. Min Act: -0.1700
Data Index: 4038599 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.5847. Min Act: -0.1700
Data Index: 7230907 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.4909. Min Act: -0.1700
Data Index: 4038596 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.4909. Min Act: -0.1700
Data Index: 3180017 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.4597. Min Act: -0.1700
Data Index: 3715783 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.4597. Min Act: -0.1700
Data Index: 1544889 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.4597. Min Act: -0.1700
Data Index: 7880171 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.3034. Min Act: -0.1700
Data Index: 6949523 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.2722. Min Act: -0.1700
Data Index: 7196637 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.2409. Min Act: -0.1700
Data Index: 5347202 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.2409. Min Act: -0.1700
Data Index: 7077266 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.2409. Min Act: -0.1700
Data Index: 475307 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.2097. Min Act: -0.1700
Data Index: 2077235 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.2097. Min Act: -0.1700
Data Index: 4420413 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.1784. Min Act: -0.1700
Data Index: 2385369 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.1784. Min Act: -0.1700
Data Index: 5727491 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.1784. Min Act: -0.1700
Data Index: 8713390 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9909. Min Range: -7.9909
Max Act: 7.1472. Min Act: -0.1700
Data Index: 1854826 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19