Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6260 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.8428. Min Act: -0.1700
Data Index: 1525841 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.4053. Min Act: -0.1700
Data Index: 7063959 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.3428. Min Act: -0.1700
Data Index: 8197420 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.3428. Min Act: -0.1700
Data Index: 5004102 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.2803. Min Act: -0.1700
Data Index: 6282832 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.2803. Min Act: -0.1700
Data Index: 3679832 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.2178. Min Act: -0.1700
Data Index: 5965029 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.1553. Min Act: -0.1700
Data Index: 2384058 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.0928. Min Act: -0.1700
Data Index: 928783 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.0928. Min Act: -0.1700
Data Index: 867944 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8428. Min Range: -8.8428
Max Act: 8.0303. Min Act: -0.1700
Data Index: 1400518 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9678. Min Act: -0.1700
Data Index: 441843 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9678. Min Act: -0.1700
Data Index: 947784 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9678. Min Act: -0.1700
Data Index: 7850079 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9053. Min Act: -0.1700
Data Index: 1505354 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9053. Min Act: -0.1700
Data Index: 2416280 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9053. Min Act: -0.1700
Data Index: 6487401 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9053. Min Act: -0.1700
Data Index: 1551806 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.9053. Min Act: -0.1700
Data Index: 6152871 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8428. Min Range: -8.8428
Max Act: 7.8428. Min Act: -0.1700
Data Index: 702247 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19