Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5490 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.9973. Min Act: -0.1700
Data Index: 3259126 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.8723. Min Act: -0.1700
Data Index: 1681585 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.9348. Min Act: -0.1700
Data Index: 5929495 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.8723. Min Act: -0.1700
Data Index: 2251508 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.7785. Min Act: -0.1700
Data Index: 6946343 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.7160. Min Act: -0.1700
Data Index: 5384109 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.7160. Min Act: -0.1700
Data Index: 2645862 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.6848. Min Act: -0.1700
Data Index: 8258528 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.6535. Min Act: -0.1700
Data Index: 5675785 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.6223. Min Act: -0.1700
Data Index: 3185607 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.5910. Min Act: -0.1700
Data Index: 3254678 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.5285. Min Act: -0.1700
Data Index: 4397819 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.5285. Min Act: -0.1700
Data Index: 782833 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.5285. Min Act: -0.1700
Data Index: 4938061 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.4973. Min Act: -0.1700
Data Index: 2194158 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.4973. Min Act: -0.1700
Data Index: 8819826 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.4660. Min Act: -0.1700
Data Index: 8310271 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.4348. Min Act: -0.1700
Data Index: 3926450 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.4660. Min Act: -0.1700
Data Index: 6545964 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9973. Min Range: -7.9973
Max Act: 7.4035. Min Act: -0.1700
Data Index: 4606186 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19