Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.9436. Min Act: -0.1700
Data Index: 3240833 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.5999. Min Act: -0.1700
Data Index: 8805470 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.4436. Min Act: -0.1700
Data Index: 6566979 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.3186. Min Act: -0.1700
Data Index: 1143373 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.2874. Min Act: -0.1700
Data Index: 2505788 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.2561. Min Act: -0.1700
Data Index: 3949925 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.1936. Min Act: -0.1700
Data Index: 7730356 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.2249. Min Act: -0.1700
Data Index: 7480763 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.1936. Min Act: -0.1700
Data Index: 89488 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.1624. Min Act: -0.1700
Data Index: 2987134 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0999. Min Act: -0.1700
Data Index: 2085767 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0999. Min Act: -0.1700
Data Index: 4745658 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0999. Min Act: -0.1700
Data Index: 7701722 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0686. Min Act: -0.1700
Data Index: 3123467 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0374. Min Act: -0.1700
Data Index: 7021422 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0686. Min Act: -0.1700
Data Index: 5916267 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0999. Min Act: -0.1700
Data Index: 1657694 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0686. Min Act: -0.1700
Data Index: 894048 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0686. Min Act: -0.1700
Data Index: 3829284 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9436. Min Range: -7.9436
Max Act: 7.0686. Min Act: -0.1700
Data Index: 883107 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19