Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.3791. Min Act: -0.1700
Data Index: 2386611 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.3479. Min Act: -0.1700
Data Index: 4376146 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.3166. Min Act: -0.1700
Data Index: 5011994 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.2854. Min Act: -0.1700
Data Index: 6792723 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.2229. Min Act: -0.1700
Data Index: 5177910 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.1291. Min Act: -0.1700
Data Index: 758997 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0666. Min Act: -0.1700
Data Index: 4506015 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 1628205 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 5769829 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 4259686 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 3819198 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0041. Min Act: -0.1700
Data Index: 494278 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 6860276 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2311552 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2864527 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.9416. Min Act: -0.1700
Data Index: 7188485 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.9416. Min Act: -0.1700
Data Index: 7195269 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.9729. Min Act: -0.1700
Data Index: 8056971 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4138761 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.9729. Min Act: -0.1700
Data Index: 5819762 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19