Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.9643. Min Act: -0.1700
Data Index: 4901647 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.9330. Min Act: -0.1700
Data Index: 4399418 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.9018. Min Act: -0.1700
Data Index: 8430341 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.9018. Min Act: -0.1700
Data Index: 3736228 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.8705. Min Act: -0.1700
Data Index: 7013884 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.8393. Min Act: -0.1700
Data Index: 2156329 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.8393. Min Act: -0.1700
Data Index: 1458529 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7768. Min Act: -0.1700
Data Index: 596444 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.8080. Min Act: -0.1700
Data Index: 5720418 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.8080. Min Act: -0.1700
Data Index: 6935848 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7768. Min Act: -0.1700
Data Index: 3285200 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7768. Min Act: -0.1700
Data Index: 2322923 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7455. Min Act: -0.1700
Data Index: 8790328 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7455. Min Act: -0.1700
Data Index: 4513199 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7455. Min Act: -0.1700
Data Index: 8728684 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7455. Min Act: -0.1700
Data Index: 2416594 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7455. Min Act: -0.1700
Data Index: 3533134 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7143. Min Act: -0.1700
Data Index: 5614407 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7143. Min Act: -0.1700
Data Index: 4779420 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9643. Min Range: -4.9643
Max Act: 4.7143. Min Act: -0.1700
Data Index: 6910826 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19