Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.9547. Min Act: -0.1700
Data Index: 5279585 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.5172. Min Act: -0.1700
Data Index: 4573074 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.3297. Min Act: -0.1700
Data Index: 4222033 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.2047. Min Act: -0.1700
Data Index: 8264361 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.1422. Min Act: -0.1700
Data Index: 5282403 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0797. Min Act: -0.1700
Data Index: 7028536 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0797. Min Act: -0.1700
Data Index: 2638573 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0172. Min Act: -0.1700
Data Index: 2977690 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0172. Min Act: -0.1700
Data Index: 2042041 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0172. Min Act: -0.1700
Data Index: 2897207 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8922. Min Act: -0.1700
Data Index: 1607640 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 5468805 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 6151833 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 4008585 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8922. Min Act: -0.1700
Data Index: 3431989 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8922. Min Act: -0.1699
Data Index: 197547 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 7569229 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8297. Min Act: -0.1700
Data Index: 1158246 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8297. Min Act: -0.1700
Data Index: 1710328 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8297. Min Act: -0.1700
Data Index: 6595361 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19