Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 530 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.6943. Min Act: -0.1700
Data Index: 5772957 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.5693. Min Act: -0.1700
Data Index: 6758291 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4756. Min Act: -0.1700
Data Index: 8163643 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4756. Min Act: -0.1700
Data Index: 2404928 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4756. Min Act: -0.1700
Data Index: 2099936 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4756. Min Act: -0.1700
Data Index: 5185677 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4443. Min Act: -0.1700
Data Index: 714676 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4131. Min Act: -0.1700
Data Index: 23646 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4131. Min Act: -0.1700
Data Index: 7958873 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4131. Min Act: -0.1700
Data Index: 6007911 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4443. Min Act: -0.1700
Data Index: 4133882 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3818. Min Act: -0.1700
Data Index: 1869309 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3818. Min Act: -0.1700
Data Index: 3603787 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.4131. Min Act: -0.1700
Data Index: 2057580 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3506. Min Act: -0.1700
Data Index: 4445129 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3506. Min Act: -0.1700
Data Index: 7016106 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3506. Min Act: -0.1700
Data Index: 1101767 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3193. Min Act: -0.1700
Data Index: 2519323 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3506. Min Act: -0.1700
Data Index: 8432840 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6943. Min Range: -5.6943
Max Act: 5.3506. Min Act: -0.1700
Data Index: 5729704 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19