Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5227 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.5933. Min Act: -0.1700
Data Index: 8560972 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.5308. Min Act: -0.1700
Data Index: 3361404 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.2495. Min Act: -0.1700
Data Index: 8319366 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.2808. Min Act: -0.1700
Data Index: 8043283 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.2808. Min Act: -0.1700
Data Index: 8487532 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.2183. Min Act: -0.1700
Data Index: 3475658 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.1870. Min Act: -0.1700
Data Index: 8812372 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.1558. Min Act: -0.1700
Data Index: 8672768 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.0933. Min Act: -0.1700
Data Index: 7897228 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.0933. Min Act: -0.1700
Data Index: 6659078 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9995. Min Act: -0.1700
Data Index: 4839942 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9995. Min Act: -0.1700
Data Index: 4881371 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5933. Min Range: -7.5933
Max Act: 7.0308. Min Act: -0.1700
Data Index: 5155041 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9995. Min Act: -0.1700
Data Index: 2249805 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9995. Min Act: -0.1700
Data Index: 1005642 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9683. Min Act: -0.1700
Data Index: 5855184 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9683. Min Act: -0.1700
Data Index: 3220588 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9683. Min Act: -0.1700
Data Index: 8089946 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9058. Min Act: -0.1700
Data Index: 1146961 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5933. Min Range: -7.5933
Max Act: 6.9683. Min Act: -0.1700
Data Index: 8220755 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19