Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0987. Min Range: -4.0987
Max Act: 4.0987. Min Act: -0.1700
Data Index: 7623040 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0987. Min Range: -4.0987
Max Act: 4.0987. Min Act: -0.1700
Data Index: 53012 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0987. Min Range: -4.0987
Max Act: 4.0362. Min Act: -0.1700
Data Index: 25658 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0987. Min Range: -4.0987
Max Act: 4.0049. Min Act: -0.1700
Data Index: 3244612 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.9736. Min Act: -0.1700
Data Index: 4169028 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.9736. Min Act: -0.1700
Data Index: 3721538 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.9424. Min Act: -0.1700
Data Index: 2077706 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8799. Min Act: -0.1700
Data Index: 1602061 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8799. Min Act: -0.1700
Data Index: 651501 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8799. Min Act: -0.1700
Data Index: 8228188 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8799. Min Act: -0.1700
Data Index: 2165766 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8799. Min Act: -0.1700
Data Index: 2080645 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8486. Min Act: -0.1700
Data Index: 3093607 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8486. Min Act: -0.1700
Data Index: 2588672 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8486. Min Act: -0.1700
Data Index: 708985 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8173. Min Act: -0.1700
Data Index: 4142781 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8330. Min Act: -0.1700
Data Index: 5977191 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8330. Min Act: -0.1700
Data Index: 6533278 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8017. Min Act: -0.1700
Data Index: 4301720 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0987. Min Range: -4.0987
Max Act: 3.8330. Min Act: -0.1700
Data Index: 4963640 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19