Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5786 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.5240. Min Act: -0.1700
Data Index: 4624180 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.4928. Min Act: -0.1700
Data Index: 5235009 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.3678. Min Act: -0.1700
Data Index: 6100038 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.3990. Min Act: -0.1700
Data Index: 6360573 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.3678. Min Act: -0.1700
Data Index: 5467275 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.3053. Min Act: -0.1700
Data Index: 6948282 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2740. Min Act: -0.1700
Data Index: 6594050 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2740. Min Act: -0.1700
Data Index: 7345662 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2740. Min Act: -0.1700
Data Index: 1907521 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2428. Min Act: -0.1700
Data Index: 573701 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2428. Min Act: -0.1700
Data Index: 1232779 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2428. Min Act: -0.1700
Data Index: 1706968 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2428. Min Act: -0.1700
Data Index: 4232941 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2115. Min Act: -0.1700
Data Index: 6150069 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2115. Min Act: -0.1700
Data Index: 1884284 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2115. Min Act: -0.1700
Data Index: 528734 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.2115. Min Act: -0.1700
Data Index: 7735409 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.1490. Min Act: -0.1700
Data Index: 903359 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.1803. Min Act: -0.1700
Data Index: 5930755 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5240. Min Range: -6.5240
Max Act: 6.1803. Min Act: -0.1700
Data Index: 7165654 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19