Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.4205. Min Act: -0.1699
Data Index: 5161072 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.0748. Min Act: -0.1700
Data Index: 4648097 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.8055. Min Act: -0.1700
Data Index: 3023339 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.7737. Min Act: -0.1700
Data Index: 7820564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.7098. Min Act: -0.1700
Data Index: 3848830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.7098. Min Act: -0.1700
Data Index: 2560246 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.6136. Min Act: -0.1700
Data Index: 8655890 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.5168. Min Act: -0.1700
Data Index: 5541959 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.5330. Min Act: -0.1700
Data Index: 5161071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.4844. Min Act: -0.1700
Data Index: 7624595 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.4357. Min Act: -0.1700
Data Index: 7624596 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3867. Min Act: -0.1700
Data Index: 6966699 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3867. Min Act: -0.1700
Data Index: 5541958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3704. Min Act: -0.1700
Data Index: 7624593 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3704. Min Act: -0.1700
Data Index: 8655887 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3540. Min Act: -0.1700
Data Index: 3023337 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3376. Min Act: -0.1700
Data Index: 8438871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3540. Min Act: -0.1700
Data Index: 3023340 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3376. Min Act: -0.1700
Data Index: 7624601 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4205. Min Range: -3.4205
Max Act: 2.3048. Min Act: -0.1700
Data Index: 5013167 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19