Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 189 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1745. Min Range: -6.1745
Max Act: 6.1745. Min Act: -0.1700
Data Index: 4089582 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1745. Min Range: -6.1745
Max Act: 6.0183. Min Act: -0.1700
Data Index: 1203357 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.8933. Min Act: -0.1700
Data Index: 974684 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.8620. Min Act: -0.1700
Data Index: 4322263 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.7995. Min Act: -0.1700
Data Index: 5131651 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.7683. Min Act: -0.1700
Data Index: 7337965 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.7683. Min Act: -0.1700
Data Index: 4369356 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.7058. Min Act: -0.1700
Data Index: 6278385 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.6745. Min Act: -0.1700
Data Index: 100240 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.6745. Min Act: -0.1700
Data Index: 1196094 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.6745. Min Act: -0.1700
Data Index: 845736 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.6433. Min Act: -0.1700
Data Index: 4086405 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.6120. Min Act: -0.1700
Data Index: 1944532 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.5808. Min Act: -0.1700
Data Index: 1201442 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.6120. Min Act: -0.1700
Data Index: 2730991 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.6120. Min Act: -0.1700
Data Index: 2520381 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.5808. Min Act: -0.1700
Data Index: 6638450 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.5808. Min Act: -0.1700
Data Index: 3249260 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.5808. Min Act: -0.1700
Data Index: 1517519 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1745. Min Range: -6.1745
Max Act: 5.5495. Min Act: -0.1700
Data Index: 1933655 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19