Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4364 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.7205. Min Act: -0.1700
Data Index: 4148789 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.4080. Min Act: -0.1700
Data Index: 1930492 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3767. Min Act: -0.1700
Data Index: 8718620 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3767. Min Act: -0.1700
Data Index: 8007412 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3767. Min Act: -0.1700
Data Index: 2607284 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3767. Min Act: -0.1700
Data Index: 6360454 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3767. Min Act: -0.1700
Data Index: 2986881 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3142. Min Act: -0.1700
Data Index: 5539100 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3455. Min Act: -0.1700
Data Index: 7696840 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3455. Min Act: -0.1700
Data Index: 8424573 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3767. Min Act: -0.1700
Data Index: 2802469 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3142. Min Act: -0.1700
Data Index: 6474835 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.2830. Min Act: -0.1700
Data Index: 7135274 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.2830. Min Act: -0.1700
Data Index: 4653222 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.3142. Min Act: -0.1700
Data Index: 217320 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.2830. Min Act: -0.1700
Data Index: 7670051 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.2517. Min Act: -0.1700
Data Index: 3998156 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.2517. Min Act: -0.1700
Data Index: 1470296 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.2205. Min Act: -0.1700
Data Index: 6047660 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7205. Min Range: -6.7205
Max Act: 6.2517. Min Act: -0.1700
Data Index: 7979571 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19