Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1983 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0976. Min Range: -8.0976
Max Act: 8.0976. Min Act: -0.1700
Data Index: 2923800 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.6914. Min Act: -0.1700
Data Index: 3399723 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.6601. Min Act: -0.1700
Data Index: 5997188 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.5351. Min Act: -0.1700
Data Index: 4110486 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.4414. Min Act: -0.1700
Data Index: 6845145 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.2226. Min Act: -0.1700
Data Index: 5705213 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.0976. Min Act: -0.1700
Data Index: 4399019 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.0664. Min Act: -0.1700
Data Index: 624297 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0976. Min Range: -8.0976
Max Act: 7.0039. Min Act: -0.1700
Data Index: 4827795 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.9414. Min Act: -0.1700
Data Index: 2383003 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.9414. Min Act: -0.1700
Data Index: 4782941 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.8789. Min Act: -0.1700
Data Index: 5955750 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.8476. Min Act: -0.1700
Data Index: 3108478 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.7851. Min Act: -0.1700
Data Index: 4995221 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.7539. Min Act: -0.1700
Data Index: 5567024 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.6914. Min Act: -0.1700
Data Index: 4733172 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.7226. Min Act: -0.1700
Data Index: 7054574 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.7226. Min Act: -0.1700
Data Index: 6570692 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.6601. Min Act: -0.1700
Data Index: 1999748 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0976. Min Range: -8.0976
Max Act: 6.6289. Min Act: -0.1700
Data Index: 1947873 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19