Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4766 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2930. Min Range: -8.2930
Max Act: 8.2930. Min Act: -0.1700
Data Index: 1663479 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2930. Min Range: -8.2930
Max Act: 8.0117. Min Act: -0.1700
Data Index: 1663485 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.7617. Min Act: -0.1700
Data Index: 2724393 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.6055. Min Act: -0.1700
Data Index: 8163548 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.6055. Min Act: -0.1700
Data Index: 3855293 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.5742. Min Act: -0.1700
Data Index: 3755948 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.4805. Min Act: -0.1700
Data Index: 7580930 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.5117. Min Act: -0.1700
Data Index: 7568819 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.4180. Min Act: -0.1700
Data Index: 5359413 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.3242. Min Act: -0.1700
Data Index: 3027013 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.2617. Min Act: -0.1700
Data Index: 5344291 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.1992. Min Act: -0.1700
Data Index: 5989309 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.2305. Min Act: -0.1700
Data Index: 4321948 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.1992. Min Act: -0.1700
Data Index: 6826339 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.1992. Min Act: -0.1700
Data Index: 2661675 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.1680. Min Act: -0.1700
Data Index: 419424 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.1055. Min Act: -0.1700
Data Index: 2788898 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.1055. Min Act: -0.1700
Data Index: 5303526 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.1055. Min Act: -0.1700
Data Index: 7350644 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2930. Min Range: -8.2930
Max Act: 7.0742. Min Act: -0.1700
Data Index: 6581309 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19