Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.7586. Min Act: -0.1700
Data Index: 2145893 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.5711. Min Act: -0.1700
Data Index: 5219888 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.3211. Min Act: -0.1700
Data Index: 2348693 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.3211. Min Act: -0.1700
Data Index: 7042057 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.1961. Min Act: -0.1700
Data Index: 5944939 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.0711. Min Act: -0.1700
Data Index: 367504 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.1336. Min Act: -0.1700
Data Index: 4503153 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7586. Min Range: -12.7586
Max Act: 12.0086. Min Act: -0.1700
Data Index: 2553313 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.9461. Min Act: -0.1700
Data Index: 4070080 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.9461. Min Act: -0.1700
Data Index: 6833455 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.8836. Min Act: -0.1700
Data Index: 2068290 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.8836. Min Act: -0.1700
Data Index: 6658381 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.8211. Min Act: -0.1700
Data Index: 661596 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.8836. Min Act: -0.1700
Data Index: 1078871 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.8211. Min Act: -0.1700
Data Index: 2758281 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.7586. Min Act: -0.1700
Data Index: 386844 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.7586. Min Act: -0.1700
Data Index: 2403388 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.6961. Min Act: -0.1700
Data Index: 6748990 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.7586. Min Act: -0.1700
Data Index: 2948749 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7586. Min Range: -12.7586
Max Act: 11.6336. Min Act: -0.1700
Data Index: 2604817 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19