Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 767 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.9121. Min Act: -0.1700
Data Index: 945689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.8495. Min Act: -0.1700
Data Index: 3163524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 1711845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.8183. Min Act: -0.1700
Data Index: 3203353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 5150782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 6484895 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 8452676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 4675964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7557. Min Act: -0.1700
Data Index: 4053362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 1358339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 3833069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7557. Min Act: -0.1700
Data Index: 64411 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7870. Min Act: -0.1700
Data Index: 1983969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7557. Min Act: -0.1700
Data Index: 102965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7244. Min Act: -0.1700
Data Index: 3680903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7557. Min Act: -0.1700
Data Index: 2173166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7244. Min Act: -0.1700
Data Index: 514336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7557. Min Act: -0.1700
Data Index: 1531973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7557. Min Act: -0.1700
Data Index: 1262205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9121. Min Range: -3.9121
Max Act: 3.7557. Min Act: -0.1700
Data Index: 1139099 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19