Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.5295. Min Act: -0.1700
Data Index: 6668330 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.4670. Min Act: -0.1700
Data Index: 2645463 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.4045. Min Act: -0.1700
Data Index: 8086166 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.4045. Min Act: -0.1700
Data Index: 1072133 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.2795. Min Act: -0.1700
Data Index: 8465847 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.2795. Min Act: -0.1700
Data Index: 3029470 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.2483. Min Act: -0.1700
Data Index: 46975 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.2795. Min Act: -0.1700
Data Index: 8660779 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.2170. Min Act: -0.1700
Data Index: 8127282 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.1858. Min Act: -0.1700
Data Index: 7800673 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.1545. Min Act: -0.1700
Data Index: 5455331 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.1233. Min Act: -0.1700
Data Index: 8708027 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.1233. Min Act: -0.1700
Data Index: 3588223 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.0920. Min Act: -0.1700
Data Index: 7676582 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.0608. Min Act: -0.1700
Data Index: 2997505 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.0608. Min Act: -0.1700
Data Index: 5015169 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.0608. Min Act: -0.1700
Data Index: 1337417 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.0608. Min Act: -0.1700
Data Index: 6519003 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5295. Min Range: -5.5295
Max Act: 5.0295. Min Act: -0.1700
Data Index: 2004438 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5295. Min Range: -5.5295
Max Act: 4.9983. Min Act: -0.1700
Data Index: 6363422 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19