Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6207 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0390. Min Range: -6.0390
Max Act: 6.0390. Min Act: -0.1700
Data Index: 8651657 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.8202. Min Act: -0.1700
Data Index: 959205 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.7890. Min Act: -0.1700
Data Index: 357628 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.7265. Min Act: -0.1700
Data Index: 1444157 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.6640. Min Act: -0.1700
Data Index: 3817205 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.6640. Min Act: -0.1700
Data Index: 8054609 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.6327. Min Act: -0.1700
Data Index: 7770848 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.6327. Min Act: -0.1700
Data Index: 1718618 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.6015. Min Act: -0.1700
Data Index: 254685 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.6015. Min Act: -0.1700
Data Index: 4045894 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5702. Min Act: -0.1700
Data Index: 2868762 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5702. Min Act: -0.1700
Data Index: 1833463 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5390. Min Act: -0.1700
Data Index: 746181 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5702. Min Act: -0.1700
Data Index: 7853933 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5702. Min Act: -0.1700
Data Index: 1228699 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5702. Min Act: -0.1700
Data Index: 434293 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5702. Min Act: -0.1700
Data Index: 3952097 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5390. Min Act: -0.1700
Data Index: 3530296 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5390. Min Act: -0.1700
Data Index: 3810394 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0390. Min Range: -6.0390
Max Act: 5.5390. Min Act: -0.1700
Data Index: 1605923 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19