Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1351 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0133. Min Range: -4.0133
Max Act: 4.0133. Min Act: -0.1700
Data Index: 262717 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.9352. Min Act: -0.1700
Data Index: 7058246 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.8726. Min Act: -0.1700
Data Index: 5775959 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.8101. Min Act: -0.1700
Data Index: 4698996 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7945. Min Act: -0.1700
Data Index: 3287287 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.8101. Min Act: -0.1700
Data Index: 4756901 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7945. Min Act: -0.1700
Data Index: 7983428 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7788. Min Act: -0.1700
Data Index: 7983427 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.8101. Min Act: -0.1700
Data Index: 8413039 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.8101. Min Act: -0.1700
Data Index: 1992334 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7788. Min Act: -0.1700
Data Index: 6039762 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7632. Min Act: -0.1700
Data Index: 1964484 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7788. Min Act: -0.1700
Data Index: 3795061 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7632. Min Act: -0.1700
Data Index: 1132276 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7788. Min Act: -0.1700
Data Index: 7343409 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7945. Min Act: -0.1700
Data Index: 3884571 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7632. Min Act: -0.1700
Data Index: 3575191 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7475. Min Act: -0.1700
Data Index: 764472 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7632. Min Act: -0.1700
Data Index: 6975046 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0133. Min Range: -4.0133
Max Act: 3.7788. Min Act: -0.1700
Data Index: 5534370 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19