Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5818 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2141. Min Range: -5.2141
Max Act: 5.2141. Min Act: -0.1700
Data Index: 4365406 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2141. Min Range: -5.2141
Max Act: 5.1204. Min Act: -0.1700
Data Index: 8615722 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2141. Min Range: -5.2141
Max Act: 5.0579. Min Act: -0.1700
Data Index: 4510895 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2141. Min Range: -5.2141
Max Act: 5.0579. Min Act: -0.1700
Data Index: 4093731 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2141. Min Range: -5.2141
Max Act: 5.0266. Min Act: -0.1700
Data Index: 6554064 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2141. Min Range: -5.2141
Max Act: 5.0266. Min Act: -0.1700
Data Index: 4973558 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2141. Min Range: -5.2141
Max Act: 5.0266. Min Act: -0.1700
Data Index: 180376 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9641. Min Act: -0.1700
Data Index: 6236025 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9329. Min Act: -0.1700
Data Index: 4692973 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9641. Min Act: -0.1700
Data Index: 1863094 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9641. Min Act: -0.1700
Data Index: 340171 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9329. Min Act: -0.1700
Data Index: 4044688 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9641. Min Act: -0.1700
Data Index: 4494238 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9641. Min Act: -0.1700
Data Index: 3376487 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9641. Min Act: -0.1700
Data Index: 2717329 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9641. Min Act: -0.1700
Data Index: 1197903 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9329. Min Act: -0.1700
Data Index: 1040089 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9329. Min Act: -0.1700
Data Index: 494125 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9329. Min Act: -0.1700
Data Index: 6448132 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2141. Min Range: -5.2141
Max Act: 4.9329. Min Act: -0.1700
Data Index: 1757654 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19