Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.6046. Min Act: -0.1700
Data Index: 8102744 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.5109. Min Act: -0.1700
Data Index: 4916975 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.4796. Min Act: -0.1700
Data Index: 441217 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.4484. Min Act: -0.1699
Data Index: 974294 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.4171. Min Act: -0.1700
Data Index: 3823585 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 2920006 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3859. Min Act: -0.1700
Data Index: 8799881 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 4585320 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3859. Min Act: -0.1700
Data Index: 7716393 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3859. Min Act: -0.1700
Data Index: 6464782 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3859. Min Act: -0.1700
Data Index: 4071698 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 2061746 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 6592132 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 4182214 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 2098720 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 1028673 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 3513230 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3546. Min Act: -0.1700
Data Index: 4128053 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3234. Min Act: -0.1700
Data Index: 3584713 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6046. Min Range: -5.6046
Max Act: 5.3234. Min Act: -0.1700
Data Index: 4017016 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19