Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.9530. Min Act: -0.1700
Data Index: 7144233 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.9361. Min Act: -0.1700
Data Index: 7919743 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.9361. Min Act: -0.1700
Data Index: 3629867 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8849. Min Act: -0.1700
Data Index: 1488912 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8849. Min Act: -0.1700
Data Index: 3302908 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8507. Min Act: -0.1700
Data Index: 1804840 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8336. Min Act: -0.1700
Data Index: 149722 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8336. Min Act: -0.1700
Data Index: 1036133 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8164. Min Act: -0.1700
Data Index: 4900579 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8336. Min Act: -0.1700
Data Index: 4560268 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8164. Min Act: -0.1700
Data Index: 7270813 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8336. Min Act: -0.1700
Data Index: 3535039 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.7992. Min Act: -0.1700
Data Index: 8716027 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8164. Min Act: -0.1700
Data Index: 8088731 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8164. Min Act: -0.1700
Data Index: 1906381 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.8164. Min Act: -0.1700
Data Index: 543632 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.7648. Min Act: -0.1700
Data Index: 3313016 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.7820. Min Act: -0.1700
Data Index: 2956141 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.7992. Min Act: -0.1700
Data Index: 5474382 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9530. Min Range: -1.9530
Max Act: 1.7992. Min Act: -0.1700
Data Index: 3222674 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19