Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5383 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9971. Min Act: -0.1700
Data Index: 4816122 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9033. Min Act: -0.1700
Data Index: 1545662 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.8721. Min Act: -0.1700
Data Index: 6062596 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.8408. Min Act: -0.1700
Data Index: 6236832 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 3408722 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7158. Min Act: -0.1700
Data Index: 4582982 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.6221. Min Act: -0.1700
Data Index: 1010338 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.6221. Min Act: -0.1700
Data Index: 5643006 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.5908. Min Act: -0.1700
Data Index: 2087953 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.5596. Min Act: -0.1700
Data Index: 3047743 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.4971. Min Act: -0.1700
Data Index: 8649388 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.4971. Min Act: -0.1700
Data Index: 7856049 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.4971. Min Act: -0.1700
Data Index: 4884317 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.4971. Min Act: -0.1700
Data Index: 6578622 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.4346. Min Act: -0.1700
Data Index: 2754773 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.4033. Min Act: -0.1700
Data Index: 7220661 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.3721. Min Act: -0.1700
Data Index: 4565754 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.4033. Min Act: -0.1700
Data Index: 8726590 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.3721. Min Act: -0.1700
Data Index: 8522915 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.3721. Min Act: -0.1700
Data Index: 3509205 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19