Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2447 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0935. Min Range: -7.0935
Max Act: 7.0935. Min Act: -0.1700
Data Index: 4730952 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0935. Min Range: -7.0935
Max Act: 7.0935. Min Act: -0.1700
Data Index: 4730951 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0935. Min Range: -7.0935
Max Act: 7.0310. Min Act: -0.1700
Data Index: 4382374 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.9997. Min Act: -0.1700
Data Index: 2008282 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.9997. Min Act: -0.1700
Data Index: 4382370 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.9685. Min Act: -0.1700
Data Index: 184468 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.9060. Min Act: -0.1700
Data Index: 4382373 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.8435. Min Act: -0.1700
Data Index: 2858154 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.8435. Min Act: -0.1700
Data Index: 4382371 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.8122. Min Act: -0.1700
Data Index: 184471 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.8122. Min Act: -0.1700
Data Index: 184469 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.7497. Min Act: -0.1700
Data Index: 184467 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.7185. Min Act: -0.1700
Data Index: 184470 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.6247. Min Act: -0.1700
Data Index: 4382376 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.5935. Min Act: -0.1700
Data Index: 184472 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.4997. Min Act: -0.1700
Data Index: 4673748 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.4685. Min Act: -0.1700
Data Index: 213656 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.3747. Min Act: -0.1700
Data Index: 1399415 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.4060. Min Act: -0.1700
Data Index: 1195805 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0935. Min Range: -7.0935
Max Act: 6.3747. Min Act: -0.1700
Data Index: 1573677 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19