Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1199 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0620. Min Range: -4.0620
Max Act: 4.0620. Min Act: -0.1700
Data Index: 5807861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0620. Min Range: -4.0620
Max Act: 4.0620. Min Act: -0.1700
Data Index: 1344566 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0620. Min Range: -4.0620
Max Act: 4.0620. Min Act: -0.1700
Data Index: 4729766 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0620. Min Range: -4.0620
Max Act: 4.0620. Min Act: -0.1700
Data Index: 1541423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9994. Min Act: -0.1700
Data Index: 5662836 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9994. Min Act: -0.1700
Data Index: 6034927 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9994. Min Act: -0.1699
Data Index: 2648322 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9994. Min Act: -0.1700
Data Index: 7575964 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9994. Min Act: -0.1700
Data Index: 8558293 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9994. Min Act: -0.1700
Data Index: 8564857 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 80510 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 2489551 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 4982260 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 4901540 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 4366121 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 4352168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 1890721 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1699
Data Index: 1427938 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9369. Min Act: -0.1700
Data Index: 278190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0620. Min Range: -4.0620
Max Act: 3.9682. Min Act: -0.1700
Data Index: 1824443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19