Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 609 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6319. Min Range: -8.6319
Max Act: 8.6319. Min Act: -0.1700
Data Index: 5566140 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6319. Min Range: -8.6319
Max Act: 8.5069. Min Act: -0.1700
Data Index: 3978287 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6319. Min Range: -8.6319
Max Act: 8.4444. Min Act: -0.1700
Data Index: 8323536 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6319. Min Range: -8.6319
Max Act: 8.1944. Min Act: -0.1700
Data Index: 1255744 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6319. Min Range: -8.6319
Max Act: 8.1319. Min Act: -0.1700
Data Index: 2702723 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6319. Min Range: -8.6319
Max Act: 8.1006. Min Act: -0.1700
Data Index: 4833434 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6319. Min Range: -8.6319
Max Act: 8.0069. Min Act: -0.1700
Data Index: 5422191 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.8819. Min Act: -0.1700
Data Index: 1884846 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.8194. Min Act: -0.1700
Data Index: 3680908 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.7569. Min Act: -0.1700
Data Index: 1787574 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.7881. Min Act: -0.1700
Data Index: 1609225 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.8194. Min Act: -0.1700
Data Index: 1562749 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.7256. Min Act: -0.1700
Data Index: 4431885 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.7256. Min Act: -0.1700
Data Index: 5386663 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.6944. Min Act: -0.1700
Data Index: 140141 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.7256. Min Act: -0.1700
Data Index: 2452947 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.6631. Min Act: -0.1700
Data Index: 7427214 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.6319. Min Act: -0.1700
Data Index: 8588229 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.6006. Min Act: -0.1700
Data Index: 4400180 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6319. Min Range: -8.6319
Max Act: 7.5694. Min Act: -0.1700
Data Index: 5334828 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19