Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2329 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.4578. Min Act: -0.1700
Data Index: 2908709 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.2078. Min Act: -0.1700
Data Index: 8195677 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0516. Min Act: -0.1700
Data Index: 6874673 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0203. Min Act: -0.1700
Data Index: 123070 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0516. Min Act: -0.1700
Data Index: 902491 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9891. Min Act: -0.1700
Data Index: 6498476 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9891. Min Act: -0.1700
Data Index: 4213428 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9578. Min Act: -0.1700
Data Index: 268307 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9578. Min Act: -0.1700
Data Index: 1823587 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9578. Min Act: -0.1700
Data Index: 2326950 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8953. Min Act: -0.1700
Data Index: 5501674 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8953. Min Act: -0.1700
Data Index: 6062324 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7852209 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7132554 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1389670 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8641. Min Act: -0.1700
Data Index: 4525049 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8328. Min Act: -0.1700
Data Index: 1162519 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8016. Min Act: -0.1700
Data Index: 835916 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8016. Min Act: -0.1700
Data Index: 7809712 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.7703. Min Act: -0.1700
Data Index: 5289480 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19