Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.6167. Min Act: -0.1700
Data Index: 522732 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3667. Min Act: -0.1700
Data Index: 7001348 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3667. Min Act: -0.1700
Data Index: 5249312 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3354. Min Act: -0.1700
Data Index: 8041434 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.2729. Min Act: -0.1700
Data Index: 6793190 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.1792. Min Act: -0.1700
Data Index: 8029381 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.2417. Min Act: -0.1700
Data Index: 3685112 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.2104. Min Act: -0.1700
Data Index: 6482747 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.1792. Min Act: -0.1700
Data Index: 5060381 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.0854. Min Act: -0.1700
Data Index: 8193786 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.0854. Min Act: -0.1700
Data Index: 7205802 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.0854. Min Act: -0.1700
Data Index: 8412882 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.0229. Min Act: -0.1700
Data Index: 789777 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6167. Min Range: -4.6167
Max Act: 3.9916. Min Act: -0.1700
Data Index: 8552971 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6167. Min Range: -4.6167
Max Act: 3.9916. Min Act: -0.1700
Data Index: 4342969 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.0229. Min Act: -0.1700
Data Index: 7520439 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.0229. Min Act: -0.1700
Data Index: 1997374 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6167. Min Range: -4.6167
Max Act: 3.9604. Min Act: -0.1700
Data Index: 2191121 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6167. Min Range: -4.6167
Max Act: 3.9916. Min Act: -0.1700
Data Index: 7129784 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6167. Min Range: -4.6167
Max Act: 3.9604. Min Act: -0.1700
Data Index: 4797922 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19