Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3270 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0778. Min Range: -3.0778
Max Act: 3.0778. Min Act: -0.1700
Data Index: 7341186 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0778. Min Range: -3.0778
Max Act: 3.0305. Min Act: -0.1700
Data Index: 4709183 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0778. Min Range: -3.0778
Max Act: 3.0147. Min Act: -0.1700
Data Index: 5950785 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9989. Min Act: -0.1700
Data Index: 8550711 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9989. Min Act: -0.1700
Data Index: 2908203 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9673. Min Act: -0.1700
Data Index: 3764293 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9831. Min Act: -0.1700
Data Index: 4596683 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9831. Min Act: -0.1700
Data Index: 2173173 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9673. Min Act: -0.1700
Data Index: 3338242 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9673. Min Act: -0.1700
Data Index: 588601 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9514. Min Act: -0.1700
Data Index: 4203323 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9673. Min Act: -0.1700
Data Index: 196736 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9673. Min Act: -0.1700
Data Index: 3830205 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9514. Min Act: -0.1700
Data Index: 5286891 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9197. Min Act: -0.1700
Data Index: 8535221 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9039. Min Act: -0.1700
Data Index: 5314528 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.9039. Min Act: -0.1700
Data Index: 7649915 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.8880. Min Act: -0.1700
Data Index: 4110051 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.8722. Min Act: -0.1700
Data Index: 1866243 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0778. Min Range: -3.0778
Max Act: 2.8722. Min Act: -0.1700
Data Index: 5074365 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19