Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2051. Min Range: -3.2051
Max Act: 3.2051. Min Act: -0.1700
Data Index: 6683325 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2051. Min Range: -3.2051
Max Act: 3.1736. Min Act: -0.1700
Data Index: 1873202 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2051. Min Range: -3.2051
Max Act: 3.0949. Min Act: -0.1700
Data Index: 1873200 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.9844. Min Act: -0.1700
Data Index: 7903807 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.9527. Min Act: -0.1700
Data Index: 6824290 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.9211. Min Act: -0.1700
Data Index: 6684489 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.9211. Min Act: -0.1700
Data Index: 1275135 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.9052. Min Act: -0.1700
Data Index: 2840562 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8894. Min Act: -0.1700
Data Index: 6034975 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 4781425 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 6684485 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 4772000 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 6684494 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 4071602 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 3701123 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 8144984 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8735. Min Act: -0.1700
Data Index: 6684481 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8576. Min Act: -0.1700
Data Index: 5334139 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8576. Min Act: -0.1700
Data Index: 4080782 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2051. Min Range: -3.2051
Max Act: 2.8417. Min Act: -0.1700
Data Index: 1387882 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19