Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4546 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.5278. Min Act: -0.1700
Data Index: 3479539 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.5591. Min Act: -0.1700
Data Index: 1700283 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.3403. Min Act: -0.1700
Data Index: 8211027 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.3403. Min Act: -0.1700
Data Index: 5155503 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.3091. Min Act: -0.1700
Data Index: 1664412 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.2778. Min Act: -0.1700
Data Index: 5863025 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.2466. Min Act: -0.1700
Data Index: 4490080 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.2153. Min Act: -0.1700
Data Index: 1483662 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 2271295 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.2153. Min Act: -0.1700
Data Index: 8176415 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 2405611 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 1622560 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 1239439 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 1832352 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 1222093 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 8398432 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1528. Min Act: -0.1700
Data Index: 1700280 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1528. Min Act: -0.1700
Data Index: 7569804 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1528. Min Act: -0.1700
Data Index: 4155978 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5591. Min Range: -4.5591
Max Act: 4.1841. Min Act: -0.1700
Data Index: 1403078 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19