Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5823 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.3646. Min Act: -0.1700
Data Index: 7874858 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.3021. Min Act: -0.1700
Data Index: 3185033 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.2084. Min Act: -0.1700
Data Index: 2472691 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.2084. Min Act: -0.1700
Data Index: 8349859 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 3433740 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 6982159 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 3485227 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 485880 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1459. Min Act: -0.1700
Data Index: 8101388 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1459. Min Act: -0.1700
Data Index: 3490444 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6758471 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6982158 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.0834. Min Act: -0.1700
Data Index: 6516581 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1146. Min Act: -0.1700
Data Index: 3453650 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1146. Min Act: -0.1700
Data Index: 6658382 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.0521. Min Act: -0.1700
Data Index: 7392412 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.0834. Min Act: -0.1700
Data Index: 3715222 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1146. Min Act: -0.1700
Data Index: 290595 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1146. Min Act: -0.1700
Data Index: 1908235 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.0834. Min Act: -0.1700
Data Index: 308107 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19