Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.1813. Min Act: -0.1700
Data Index: 3459638 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.1147. Min Act: -0.1700
Data Index: 537211 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0979. Min Act: -0.1700
Data Index: 2804570 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0812. Min Act: -0.1700
Data Index: 2753162 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0812. Min Act: -0.1700
Data Index: 5263373 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0812. Min Act: -0.1700
Data Index: 463228 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0812. Min Act: -0.1700
Data Index: 1012261 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0812. Min Act: -0.1700
Data Index: 8155491 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0644. Min Act: -0.1700
Data Index: 2209221 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0644. Min Act: -0.1700
Data Index: 2265093 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0644. Min Act: -0.1700
Data Index: 6451682 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0644. Min Act: -0.1700
Data Index: 3258131 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0476. Min Act: -0.1700
Data Index: 6205567 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0476. Min Act: -0.1700
Data Index: 8411442 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0476. Min Act: -0.1700
Data Index: 5157640 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0476. Min Act: -0.1700
Data Index: 8036086 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0644. Min Act: -0.1700
Data Index: 3870135 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0476. Min Act: -0.1700
Data Index: 6454784 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0476. Min Act: -0.1700
Data Index: 4627427 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1813. Min Range: -2.1813
Max Act: 2.0307. Min Act: -0.1700
Data Index: 1953346 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19