Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.2944. Min Act: -0.1700
Data Index: 4409472 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.2944. Min Act: -0.1700
Data Index: 5630890 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.2007. Min Act: -0.1700
Data Index: 3511854 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.1382. Min Act: -0.1700
Data Index: 5537856 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.1069. Min Act: -0.1700
Data Index: 378701 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.0444. Min Act: -0.1700
Data Index: 2478650 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.0444. Min Act: -0.1700
Data Index: 4733180 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.0444. Min Act: -0.1700
Data Index: 1904564 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2944. Min Range: -5.2944
Max Act: 5.0132. Min Act: -0.1700
Data Index: 6285812 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9819. Min Act: -0.1700
Data Index: 3886465 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9819. Min Act: -0.1700
Data Index: 7314336 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9507. Min Act: -0.1700
Data Index: 3888175 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9507. Min Act: -0.1700
Data Index: 536140 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9507. Min Act: -0.1700
Data Index: 7448145 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9507. Min Act: -0.1700
Data Index: 5019469 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9194. Min Act: -0.1700
Data Index: 2175166 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9507. Min Act: -0.1700
Data Index: 3770959 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9507. Min Act: -0.1700
Data Index: 170453 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9194. Min Act: -0.1700
Data Index: 423046 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2944. Min Range: -5.2944
Max Act: 4.9507. Min Act: -0.1700
Data Index: 6855535 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19