Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6370 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.4629. Min Act: -0.1700
Data Index: 524892 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.3066. Min Act: -0.1700
Data Index: 4499214 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.2129. Min Act: -0.1700
Data Index: 57973 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.2129. Min Act: -0.1700
Data Index: 3395618 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.1504. Min Act: -0.1700
Data Index: 4180558 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.1504. Min Act: -0.1700
Data Index: 4484514 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.1191. Min Act: -0.1700
Data Index: 411032 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.0566. Min Act: -0.1700
Data Index: 670387 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.0254. Min Act: -0.1700
Data Index: 6071377 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.0254. Min Act: -0.1700
Data Index: 7859063 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.0254. Min Act: -0.1700
Data Index: 8145001 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4629. Min Range: -7.4629
Max Act: 7.0254. Min Act: -0.1700
Data Index: 492063 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.9941. Min Act: -0.1700
Data Index: 1535920 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.9629. Min Act: -0.1700
Data Index: 5485466 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.9629. Min Act: -0.1700
Data Index: 7806059 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.9004. Min Act: -0.1700
Data Index: 3648995 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.8691. Min Act: -0.1700
Data Index: 6456174 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.8691. Min Act: -0.1700
Data Index: 8473131 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.8379. Min Act: -0.1700
Data Index: 8182869 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4629. Min Range: -7.4629
Max Act: 6.8066. Min Act: -0.1700
Data Index: 7650641 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19