Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.7952. Min Act: -0.1700
Data Index: 3666139 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6702. Min Act: -0.1700
Data Index: 8171484 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.7014. Min Act: -0.1700
Data Index: 4884664 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6702. Min Act: -0.1700
Data Index: 8344211 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6702. Min Act: -0.1700
Data Index: 1232213 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6702. Min Act: -0.1700
Data Index: 2295741 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6389. Min Act: -0.1700
Data Index: 3787217 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5367156 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6389. Min Act: -0.1700
Data Index: 1676329 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6389. Min Act: -0.1700
Data Index: 918113 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6077. Min Act: -0.1700
Data Index: 7336983 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6077. Min Act: -0.1700
Data Index: 6082816 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6077. Min Act: -0.1700
Data Index: 2818389 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.5764. Min Act: -0.1700
Data Index: 3532170 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.5764. Min Act: -0.1700
Data Index: 1437880 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.6077. Min Act: -0.1700
Data Index: 6214093 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.5764. Min Act: -0.1700
Data Index: 6547144 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.5764. Min Act: -0.1700
Data Index: 6955768 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.5452. Min Act: -0.1700
Data Index: 5124425 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7952. Min Range: -5.7952
Max Act: 5.5452. Min Act: -0.1700
Data Index: 4707894 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19