Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.1772. Min Range: -19.1772
Max Act: 19.1772. Min Act: -0.1700
Data Index: 1004419 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.1772. Min Range: -19.1772
Max Act: 19.1772. Min Act: -0.1700
Data Index: 2185244 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.1772. Min Range: -19.1772
Max Act: 19.1772. Min Act: -0.1700
Data Index: 1893333 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.8022. Min Act: -0.1700
Data Index: 8418537 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.8022. Min Act: -0.1700
Data Index: 6889752 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.8022. Min Act: -0.1700
Data Index: 2448475 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.8022. Min Act: -0.1700
Data Index: 566284 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.8022. Min Act: -0.1700
Data Index: 6101238 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.8022. Min Act: -0.1700
Data Index: 2286102 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.6772. Min Act: -0.1700
Data Index: 4141433 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.6772. Min Act: -0.1700
Data Index: 3231780 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.6772. Min Act: -0.1700
Data Index: 7555169 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 5723428 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 5269251 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 6739554 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 5229254 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 7496613 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 958406 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 3816594 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.1772. Min Range: -19.1772
Max Act: 18.5522. Min Act: -0.1700
Data Index: 296511 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19