Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4216 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.7943. Min Act: -0.1700
Data Index: 358403 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.6693. Min Act: -0.1700
Data Index: 7077295 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.6381. Min Act: -0.1700
Data Index: 2117551 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.6693. Min Act: -0.1700
Data Index: 5719478 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.5443. Min Act: -0.1700
Data Index: 4732173 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.5131. Min Act: -0.1700
Data Index: 4723702 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.4818. Min Act: -0.1700
Data Index: 3024439 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.4818. Min Act: -0.1700
Data Index: 1581811 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.3881. Min Act: -0.1700
Data Index: 6557449 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.3568. Min Act: -0.1700
Data Index: 6398574 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.3256. Min Act: -0.1700
Data Index: 2463574 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.3568. Min Act: -0.1700
Data Index: 8019870 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.3256. Min Act: -0.1700
Data Index: 8219662 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.2943. Min Act: -0.1700
Data Index: 2224332 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.2631. Min Act: -0.1700
Data Index: 4306508 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.2943. Min Act: -0.1700
Data Index: 2214697 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.2318. Min Act: -0.1700
Data Index: 1462926 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.2318. Min Act: -0.1700
Data Index: 3016614 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.2318. Min Act: -0.1700
Data Index: 7786734 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7943. Min Range: -6.7943
Max Act: 6.2631. Min Act: -0.1700
Data Index: 5491557 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19