Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.7353. Min Act: -0.1700
Data Index: 6577126 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.7040. Min Act: -0.1700
Data Index: 2051061 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.7040. Min Act: -0.1700
Data Index: 2755724 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 3782633 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 1569064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6727. Min Act: -0.1700
Data Index: 3393893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6727. Min Act: -0.1700
Data Index: 3058681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6727. Min Act: -0.1700
Data Index: 1298043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6727. Min Act: -0.1700
Data Index: 8746324 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6727. Min Act: -0.1700
Data Index: 6383298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6727. Min Act: -0.1700
Data Index: 4531428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6101. Min Act: -0.1699
Data Index: 2725574 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 1228423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 2513255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 2796023 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 3164088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 3409434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6101. Min Act: -0.1700
Data Index: 879496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 3554016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7353. Min Range: -3.7353
Max Act: 3.6414. Min Act: -0.1700
Data Index: 56991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19