Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.4866. Min Act: -0.1700
Data Index: 3555042 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.1741. Min Act: -0.1700
Data Index: 7880176 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.0804. Min Act: -0.1700
Data Index: 6282124 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.0804. Min Act: -0.1700
Data Index: 1101441 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.0491. Min Act: -0.1700
Data Index: 1438995 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.0179. Min Act: -0.1700
Data Index: 3712256 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.0179. Min Act: -0.1700
Data Index: 4340556 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4866. Min Range: -5.4866
Max Act: 5.0179. Min Act: -0.1700
Data Index: 2062816 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.9866. Min Act: -0.1700
Data Index: 7304841 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.9554. Min Act: -0.1700
Data Index: 4075111 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.9866. Min Act: -0.1700
Data Index: 2750619 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.9241. Min Act: -0.1700
Data Index: 2374899 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8929. Min Act: -0.1700
Data Index: 3856430 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8929. Min Act: -0.1700
Data Index: 1457586 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 321067 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 1586520 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 3194043 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 713053 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 4710363 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4866. Min Range: -5.4866
Max Act: 4.8304. Min Act: -0.1700
Data Index: 103148 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19