Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.9115. Min Act: -0.1700
Data Index: 1130802 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.9115. Min Act: -0.1700
Data Index: 2969948 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.9115. Min Act: -0.1700
Data Index: 4961465 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8957. Min Act: -0.1700
Data Index: 8558959 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8798. Min Act: -0.1700
Data Index: 6584620 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8639. Min Act: -0.1700
Data Index: 1043436 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8321. Min Act: -0.1700
Data Index: 2470492 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8480. Min Act: -0.1700
Data Index: 5488839 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8003. Min Act: -0.1700
Data Index: 1796547 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8003. Min Act: -0.1700
Data Index: 2018620 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.8003. Min Act: -0.1700
Data Index: 4355600 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7844. Min Act: -0.1700
Data Index: 3216583 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7844. Min Act: -0.1700
Data Index: 7182408 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7844. Min Act: -0.1700
Data Index: 881216 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7844. Min Act: -0.1700
Data Index: 4085531 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7844. Min Act: -0.1700
Data Index: 8360614 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7684. Min Act: -0.1700
Data Index: 594864 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7684. Min Act: -0.1700
Data Index: 7842494 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7844. Min Act: -0.1700
Data Index: 5111008 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9115. Min Range: -2.9115
Max Act: 2.7525. Min Act: -0.1700
Data Index: 7100456 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19