Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.5317. Min Act: -0.1700
Data Index: 5738754 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.2817. Min Act: -0.1700
Data Index: 4293202 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.1880. Min Act: -0.1700
Data Index: 2192054 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.1567. Min Act: -0.1700
Data Index: 5563003 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0630. Min Act: -0.1700
Data Index: 2034793 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0317. Min Act: -0.1700
Data Index: 6557994 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0005. Min Act: -0.1700
Data Index: 1198649 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0005. Min Act: -0.1700
Data Index: 2491175 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0005. Min Act: -0.1700
Data Index: 2725017 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9380. Min Act: -0.1700
Data Index: 5007715 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9692. Min Act: -0.1700
Data Index: 6047082 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9692. Min Act: -0.1700
Data Index: 8358361 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9692. Min Act: -0.1700
Data Index: 6859648 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9380. Min Act: -0.1700
Data Index: 6320402 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9380. Min Act: -0.1700
Data Index: 7985064 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8755. Min Act: -0.1700
Data Index: 6122308 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8755. Min Act: -0.1700
Data Index: 3557649 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8755. Min Act: -0.1700
Data Index: 7901736 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8442. Min Act: -0.1700
Data Index: 382298 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8442. Min Act: -0.1700
Data Index: 7646590 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19