Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 948 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 4239084 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 6746098 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 6375268 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1699
Data Index: 3127820 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 7704337 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 6864502 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 4312420 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 606415 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 1091103 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 2542516 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.4811. Min Act: -0.1700
Data Index: 2892768 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.3560. Min Act: -0.1700
Data Index: 4954345 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.3248. Min Act: -0.1700
Data Index: 4329927 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.3248. Min Act: -0.1700
Data Index: 5466232 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.3248. Min Act: -0.1700
Data Index: 5632801 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.2935. Min Act: -0.1700
Data Index: 8281772 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.2935. Min Act: -0.1700
Data Index: 8752696 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.2935. Min Act: -0.1700
Data Index: 2243234 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.2623. Min Act: -0.1700
Data Index: 6146562 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4811. Min Range: -4.4811
Max Act: 4.2623. Min Act: -0.1700
Data Index: 3723693 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19