Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.5506. Min Act: -0.1700
Data Index: 8485729 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.5193. Min Act: -0.1700
Data Index: 312692 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 7788741 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 4227707 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 1132655 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 7034112 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3631. Min Act: -0.1700
Data Index: 7913050 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3631. Min Act: -0.1700
Data Index: 8064735 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3943. Min Act: -0.1700
Data Index: 4195124 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3943. Min Act: -0.1700
Data Index: 4108088 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 7523510 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3631. Min Act: -0.1700
Data Index: 5171515 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3631. Min Act: -0.1700
Data Index: 1599391 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3318. Min Act: -0.1700
Data Index: 4161287 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3318. Min Act: -0.1700
Data Index: 7113097 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3318. Min Act: -0.1700
Data Index: 2906852 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3318. Min Act: -0.1700
Data Index: 4596526 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3318. Min Act: -0.1700
Data Index: 3596959 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3318. Min Act: -0.1700
Data Index: 7298893 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5506. Min Range: -5.5506
Max Act: 5.3318. Min Act: -0.1700
Data Index: 1934998 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19