Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.8203. Min Act: -0.1700
Data Index: 1480201 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.8203. Min Act: -0.1700
Data Index: 3079810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.7265. Min Act: -0.1700
Data Index: 2869542 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.7265. Min Act: -0.1700
Data Index: 2495140 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.7265. Min Act: -0.1700
Data Index: 4018616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.7265. Min Act: -0.1700
Data Index: 7493817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.7265. Min Act: -0.1700
Data Index: 6240783 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6953. Min Act: -0.1699
Data Index: 7910709 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6953. Min Act: -0.1700
Data Index: 8350171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6953. Min Act: -0.1699
Data Index: 3945617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6953. Min Act: -0.1700
Data Index: 6862694 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6953. Min Act: -0.1700
Data Index: 4779228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 2167103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 1186984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 4094027 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 2244612 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 4586915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 5220620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 5915056 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8203. Min Range: -4.8203
Max Act: 4.6640. Min Act: -0.1700
Data Index: 5931270 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19