Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1262 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8186. Min Range: -7.8186
Max Act: 7.8186. Min Act: -0.1700
Data Index: 1366996 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.9436. Min Act: -0.1700
Data Index: 369208 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.9124. Min Act: -0.1700
Data Index: 68717 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.8811. Min Act: -0.1700
Data Index: 1339383 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.8811. Min Act: -0.1700
Data Index: 1339382 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.8186. Min Act: -0.1700
Data Index: 4569728 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.7561. Min Act: -0.1700
Data Index: 6037044 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.7249. Min Act: -0.1700
Data Index: 369209 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.6936. Min Act: -0.1700
Data Index: 5831938 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.6311. Min Act: -0.1700
Data Index: 6193195 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5999. Min Act: -0.1700
Data Index: 2243146 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5999. Min Act: -0.1700
Data Index: 1323647 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5374. Min Act: -0.1700
Data Index: 1562327 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5999. Min Act: -0.1700
Data Index: 7534426 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5686. Min Act: -0.1700
Data Index: 279188 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5061. Min Act: -0.1700
Data Index: 7520693 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5061. Min Act: -0.1700
Data Index: 1359024 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.5061. Min Act: -0.1700
Data Index: 6193196 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.4436. Min Act: -0.1700
Data Index: 7064052 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8186. Min Range: -7.8186
Max Act: 6.4749. Min Act: -0.1700
Data Index: 385598 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19