Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 85 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.8637. Min Act: -0.1700
Data Index: 6914449 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.7522. Min Act: -0.1700
Data Index: 1171235 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.7363. Min Act: -0.1700
Data Index: 6567045 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.7363. Min Act: -0.1700
Data Index: 2718034 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.7043. Min Act: -0.1700
Data Index: 8318082 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.7043. Min Act: -0.1700
Data Index: 6761718 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6883. Min Act: -0.1700
Data Index: 8496012 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6562. Min Act: -0.1700
Data Index: 7668231 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6402. Min Act: -0.1700
Data Index: 5753458 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6402. Min Act: -0.1700
Data Index: 5878294 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6080. Min Act: -0.1700
Data Index: 7151765 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6402. Min Act: -0.1700
Data Index: 4029028 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6241. Min Act: -0.1700
Data Index: 6382894 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6241. Min Act: -0.1700
Data Index: 1977550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6080. Min Act: -0.1700
Data Index: 6809834 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6080. Min Act: -0.1700
Data Index: 235249 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6080. Min Act: -0.1700
Data Index: 5149320 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.5919. Min Act: -0.1700
Data Index: 434619 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.5919. Min Act: -0.1700
Data Index: 6027565 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8637. Min Range: -2.8637
Max Act: 2.6080. Min Act: -0.1700
Data Index: 3828652 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19