Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0117. Min Range: -2.0117
Max Act: 2.0117. Min Act: -0.1700
Data Index: 8194070 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9948. Min Act: -0.1700
Data Index: 1961488 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9779. Min Act: -0.1700
Data Index: 3541506 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9610. Min Act: -0.1700
Data Index: 1039032 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9610. Min Act: -0.1700
Data Index: 561879 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9610. Min Act: -0.1700
Data Index: 1961485 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9779. Min Act: -0.1700
Data Index: 6535938 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9779. Min Act: -0.1700
Data Index: 4551374 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9610. Min Act: -0.1700
Data Index: 3927007 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9440. Min Act: -0.1700
Data Index: 2786772 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 5601632 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 7954149 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 3927011 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 5168469 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 7931457 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 7564817 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 2878402 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9270. Min Act: -0.1700
Data Index: 2575719 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9100. Min Act: -0.1700
Data Index: 4196449 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0117. Min Range: -2.0117
Max Act: 1.9440. Min Act: -0.1700
Data Index: 3989025 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19