Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1694. Min Range: -4.1694
Max Act: 4.1694. Min Act: -0.1700
Data Index: 8068106 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1694. Min Range: -4.1694
Max Act: 4.0444. Min Act: -0.1700
Data Index: 3230736 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1694. Min Range: -4.1694
Max Act: 4.0444. Min Act: -0.1700
Data Index: 4357004 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9819. Min Act: -0.1700
Data Index: 1202874 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9819. Min Act: -0.1700
Data Index: 4052759 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9819. Min Act: -0.1700
Data Index: 1734995 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9506. Min Act: -0.1700
Data Index: 3095834 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9819. Min Act: -0.1700
Data Index: 5611877 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9506. Min Act: -0.1700
Data Index: 8221329 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9506. Min Act: -0.1700
Data Index: 221735 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9819. Min Act: -0.1700
Data Index: 1042326 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9506. Min Act: -0.1700
Data Index: 1447718 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9506. Min Act: -0.1700
Data Index: 2961556 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9193. Min Act: -0.1700
Data Index: 5628572 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.8881. Min Act: -0.1700
Data Index: 5879871 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9193. Min Act: -0.1700
Data Index: 5511230 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9193. Min Act: -0.1700
Data Index: 6088208 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9193. Min Act: -0.1700
Data Index: 3432323 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.9193. Min Act: -0.1700
Data Index: 2618344 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.8881. Min Act: -0.1700
Data Index: 7101139 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19