Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.1961. Min Act: -0.1700
Data Index: 7080465 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.1647. Min Act: -0.1700
Data Index: 4113061 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.1174. Min Act: -0.1700
Data Index: 2494730 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.1332. Min Act: -0.1700
Data Index: 7689040 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.1174. Min Act: -0.1700
Data Index: 4478935 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0859. Min Act: -0.1700
Data Index: 2326402 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0859. Min Act: -0.1700
Data Index: 1367165 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0859. Min Act: -0.1700
Data Index: 6165846 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0701. Min Act: -0.1700
Data Index: 5431572 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0701. Min Act: -0.1700
Data Index: 4590069 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0701. Min Act: -0.1700
Data Index: 3068099 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0859. Min Act: -0.1700
Data Index: 7737900 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0701. Min Act: -0.1700
Data Index: 3036372 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0544. Min Act: -0.1700
Data Index: 1737491 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0701. Min Act: -0.1700
Data Index: 4422497 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0544. Min Act: -0.1700
Data Index: 2189993 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0701. Min Act: -0.1700
Data Index: 204064 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0544. Min Act: -0.1700
Data Index: 4754353 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0701. Min Act: -0.1700
Data Index: 5386873 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1961. Min Range: -3.1961
Max Act: 3.0544. Min Act: -0.1700
Data Index: 2314973 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19