Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1781 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1373. Min Range: -6.1373
Max Act: 6.1373. Min Act: -0.1700
Data Index: 4132059 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1373. Min Range: -6.1373
Max Act: 6.0435. Min Act: -0.1700
Data Index: 8089321 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.8560. Min Act: -0.1700
Data Index: 2311974 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.8248. Min Act: -0.1700
Data Index: 4219143 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7935. Min Act: -0.1700
Data Index: 4077839 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7935. Min Act: -0.1700
Data Index: 8134142 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7623. Min Act: -0.1700
Data Index: 5026498 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7310. Min Act: -0.1700
Data Index: 3561557 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7310. Min Act: -0.1700
Data Index: 810673 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6998. Min Act: -0.1700
Data Index: 7987252 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6998. Min Act: -0.1700
Data Index: 8693142 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6998. Min Act: -0.1700
Data Index: 3433630 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6685. Min Act: -0.1700
Data Index: 6598796 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6685. Min Act: -0.1700
Data Index: 2659517 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6685. Min Act: -0.1700
Data Index: 8457560 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6685. Min Act: -0.1700
Data Index: 3584149 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6685. Min Act: -0.1700
Data Index: 5946892 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6685. Min Act: -0.1700
Data Index: 5646488 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6685. Min Act: -0.1700
Data Index: 3630950 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6373. Min Act: -0.1700
Data Index: 3139291 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19