Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.8993. Min Act: -0.1700
Data Index: 5686179 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.8368. Min Act: -0.1700
Data Index: 2504921 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.7743. Min Act: -0.1700
Data Index: 332813 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.7743. Min Act: -0.1700
Data Index: 1967564 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.6806. Min Act: -0.1700
Data Index: 7155985 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.5556. Min Act: -0.1700
Data Index: 5280835 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.4931. Min Act: -0.1700
Data Index: 2537550 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.4931. Min Act: -0.1700
Data Index: 6095341 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3993. Min Act: -0.1700
Data Index: 3057175 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3993. Min Act: -0.1700
Data Index: 8668514 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.4306. Min Act: -0.1700
Data Index: 7491191 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3993. Min Act: -0.1700
Data Index: 5242605 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3993. Min Act: -0.1700
Data Index: 6273049 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3681. Min Act: -0.1700
Data Index: 4029499 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.4306. Min Act: -0.1700
Data Index: 3579331 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3681. Min Act: -0.1700
Data Index: 1749475 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8485732 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3056. Min Act: -0.1700
Data Index: 8672772 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3056. Min Act: -0.1700
Data Index: 3323133 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8993. Min Range: -5.8993
Max Act: 5.3056. Min Act: -0.1700
Data Index: 3915957 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19