Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3631. Min Range: -6.3631
Max Act: 6.3631. Min Act: -0.1700
Data Index: 4718668 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3631. Min Range: -6.3631
Max Act: 6.3006. Min Act: -0.1700
Data Index: 8125102 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3631. Min Range: -6.3631
Max Act: 6.2068. Min Act: -0.1700
Data Index: 7430998 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3631. Min Range: -6.3631
Max Act: 6.0506. Min Act: -0.1700
Data Index: 406404 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3631. Min Range: -6.3631
Max Act: 6.0193. Min Act: -0.1700
Data Index: 7732013 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3631. Min Range: -6.3631
Max Act: 6.0193. Min Act: -0.1700
Data Index: 3370926 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.9568. Min Act: -0.1700
Data Index: 8802217 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.9256. Min Act: -0.1700
Data Index: 4475906 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.9568. Min Act: -0.1700
Data Index: 5432503 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.9256. Min Act: -0.1700
Data Index: 4959446 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8943. Min Act: -0.1700
Data Index: 6022202 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1710713 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8943. Min Act: -0.1700
Data Index: 3431786 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8631. Min Act: -0.1700
Data Index: 3171155 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8943. Min Act: -0.1700
Data Index: 547795 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8943. Min Act: -0.1700
Data Index: 2908690 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8631. Min Act: -0.1700
Data Index: 7491218 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8631. Min Act: -0.1700
Data Index: 3638782 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8631. Min Act: -0.1700
Data Index: 1912234 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3631. Min Range: -6.3631
Max Act: 5.8631. Min Act: -0.1700
Data Index: 1950795 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19