Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.8361. Min Act: -0.1700
Data Index: 7297801 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7423. Min Act: -0.1700
Data Index: 2268673 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7111. Min Act: -0.1700
Data Index: 180862 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6485. Min Act: -0.1700
Data Index: 2169394 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6485. Min Act: -0.1700
Data Index: 8012809 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6485. Min Act: -0.1700
Data Index: 4784283 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6173. Min Act: -0.1700
Data Index: 3627299 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6173. Min Act: -0.1700
Data Index: 6643072 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1701922 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5860. Min Act: -0.1700
Data Index: 4707640 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1421848 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5860. Min Act: -0.1700
Data Index: 3061975 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6173. Min Act: -0.1700
Data Index: 3696947 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5548. Min Act: -0.1700
Data Index: 1465229 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5548. Min Act: -0.1700
Data Index: 1764516 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5235. Min Act: -0.1700
Data Index: 2688831 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5548. Min Act: -0.1700
Data Index: 3332198 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5235. Min Act: -0.1700
Data Index: 6585188 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5235. Min Act: -0.1700
Data Index: 2032641 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5235. Min Act: -0.1700
Data Index: 3110904 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19