Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1690 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.5965. Min Act: -0.1700
Data Index: 6908278 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6753928 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6908280 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.4402. Min Act: -0.1700
Data Index: 6320557 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.3777. Min Act: -0.1700
Data Index: 6683537 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2309831 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.3465. Min Act: -0.1700
Data Index: 2341778 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.3152. Min Act: -0.1700
Data Index: 8247546 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.3152. Min Act: -0.1700
Data Index: 8749696 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2840. Min Act: -0.1700
Data Index: 7287119 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2840. Min Act: -0.1700
Data Index: 468647 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2215. Min Act: -0.1700
Data Index: 8321884 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2527. Min Act: -0.1700
Data Index: 6621078 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2527. Min Act: -0.1700
Data Index: 2540663 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2527. Min Act: -0.1700
Data Index: 4666930 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2527. Min Act: -0.1700
Data Index: 7259759 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2215. Min Act: -0.1700
Data Index: 8726459 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2215. Min Act: -0.1700
Data Index: 4249391 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.2215. Min Act: -0.1700
Data Index: 7187841 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5965. Min Range: -5.5965
Max Act: 5.1902. Min Act: -0.1700
Data Index: 5171434 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19