Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.8507. Min Act: -0.1700
Data Index: 7674874 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.6319. Min Act: -0.1700
Data Index: 5881675 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.6319. Min Act: -0.1696
Data Index: 5881664 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.6006. Min Act: -0.1700
Data Index: 5881665 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.6006. Min Act: -0.1700
Data Index: 5881666 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.6006. Min Act: -0.1700
Data Index: 5881674 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.5381. Min Act: -0.1700
Data Index: 8746369 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.5381. Min Act: -0.1700
Data Index: 6557586 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.5694. Min Act: -0.1700
Data Index: 7101680 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.5069. Min Act: -0.1700
Data Index: 8697142 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.5069. Min Act: -0.1700
Data Index: 5881662 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.5069. Min Act: -0.1700
Data Index: 5881671 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4756. Min Act: -0.1700
Data Index: 1906449 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4756. Min Act: -0.1700
Data Index: 3949151 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4756. Min Act: -0.1700
Data Index: 3786426 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4444. Min Act: -0.1700
Data Index: 7869787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4444. Min Act: -0.1700
Data Index: 4127945 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4756. Min Act: -0.1700
Data Index: 7208221 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4444. Min Act: -0.1700
Data Index: 1694665 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8507. Min Range: -4.8507
Max Act: 4.4131. Min Act: -0.1700
Data Index: 5170708 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19