Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.5188. Min Act: -0.1700
Data Index: 8276242 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.3313. Min Act: -0.1700
Data Index: 7206064 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.3001. Min Act: -0.1700
Data Index: 4759711 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.3001. Min Act: -0.1700
Data Index: 864950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2688. Min Act: -0.1700
Data Index: 238796 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2376. Min Act: -0.1700
Data Index: 838417 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2376. Min Act: -0.1700
Data Index: 3825565 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.3001. Min Act: -0.1700
Data Index: 7684367 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.3001. Min Act: -0.1700
Data Index: 7061101 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.1751. Min Act: -0.1700
Data Index: 6717203 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2376. Min Act: -0.1700
Data Index: 4637103 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2688. Min Act: -0.1700
Data Index: 945709 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2376. Min Act: -0.1700
Data Index: 5533470 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2063. Min Act: -0.1700
Data Index: 5777806 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2376. Min Act: -0.1700
Data Index: 4797343 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2376. Min Act: -0.1700
Data Index: 5581170 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2376. Min Act: -0.1700
Data Index: 5768755 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2063. Min Act: -0.1699
Data Index: 1773788 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2063. Min Act: -0.1700
Data Index: 5567838 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5188. Min Range: -4.5188
Max Act: 4.2063. Min Act: -0.1700
Data Index: 5630316 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19