Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4998 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.8906. Min Act: -0.1700
Data Index: 2180107 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.8281. Min Act: -0.1700
Data Index: 4045626 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.4531. Min Act: -0.1700
Data Index: 4387743 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.4843. Min Act: -0.1700
Data Index: 7387239 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.4531. Min Act: -0.1700
Data Index: 2825478 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.4218. Min Act: -0.1700
Data Index: 8066633 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.4218. Min Act: -0.1700
Data Index: 4813650 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.3906. Min Act: -0.1700
Data Index: 1273500 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.4218. Min Act: -0.1700
Data Index: 3547015 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.3906. Min Act: -0.1700
Data Index: 3205197 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.3281. Min Act: -0.1700
Data Index: 7076986 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.2968. Min Act: -0.1700
Data Index: 8558383 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.2343. Min Act: -0.1700
Data Index: 677492 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.2031. Min Act: -0.1700
Data Index: 1306096 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.1718. Min Act: -0.1700
Data Index: 6582588 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.1406. Min Act: -0.1700
Data Index: 8172801 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.1406. Min Act: -0.1700
Data Index: 5602389 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.1093. Min Act: -0.1700
Data Index: 849926 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.1093. Min Act: -0.1700
Data Index: 708734 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8906. Min Range: -6.8906
Max Act: 6.1093. Min Act: -0.1700
Data Index: 1793608 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19