Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7741. Min Act: -0.1700
Data Index: 6757414 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7741. Min Act: -0.1700
Data Index: 4931385 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7655. Min Act: -0.1700
Data Index: 8510563 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7569. Min Act: -0.1700
Data Index: 6402029 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7482. Min Act: -0.1700
Data Index: 2126286 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7482. Min Act: -0.1700
Data Index: 6150455 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7223. Min Act: -0.1700
Data Index: 2846063 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7309. Min Act: -0.1700
Data Index: 1909844 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7223. Min Act: -0.1700
Data Index: 1241815 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7223. Min Act: -0.1700
Data Index: 1929359 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7223. Min Act: -0.1700
Data Index: 8565172 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7136. Min Act: -0.1700
Data Index: 7878938 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7223. Min Act: -0.1700
Data Index: 4357019 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.6963. Min Act: -0.1700
Data Index: 2471617 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7050. Min Act: -0.1700
Data Index: 636929 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.6963. Min Act: -0.1700
Data Index: 8583617 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.6963. Min Act: -0.1700
Data Index: 2704649 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.7050. Min Act: -0.1700
Data Index: 2975492 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.6876. Min Act: -0.1700
Data Index: 6743732 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7741. Min Range: -1.7741
Max Act: 1.6876. Min Act: -0.1700
Data Index: 5008336 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19