Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.5904. Min Act: -0.1700
Data Index: 263681 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.3404. Min Act: -0.1700
Data Index: 6399829 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.3092. Min Act: -0.1700
Data Index: 8084958 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.3092. Min Act: -0.1700
Data Index: 3497039 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.2779. Min Act: -0.1700
Data Index: 4011532 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.2467. Min Act: -0.1700
Data Index: 767186 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1842. Min Act: -0.1700
Data Index: 1166965 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1842. Min Act: -0.1700
Data Index: 342456 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1842. Min Act: -0.1700
Data Index: 2657985 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1529. Min Act: -0.1700
Data Index: 590042 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1217. Min Act: -0.1700
Data Index: 8474848 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1529. Min Act: -0.1700
Data Index: 5811047 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1217. Min Act: -0.1700
Data Index: 7270818 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.1217. Min Act: -0.1700
Data Index: 1608504 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.0904. Min Act: -0.1700
Data Index: 1847931 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.0904. Min Act: -0.1700
Data Index: 6041313 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.0592. Min Act: -0.1700
Data Index: 2945037 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.0592. Min Act: -0.1700
Data Index: 6794996 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.0592. Min Act: -0.1700
Data Index: 3758591 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5904. Min Range: -5.5904
Max Act: 5.0904. Min Act: -0.1700
Data Index: 5288276 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19