Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5308 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.5380. Min Act: -0.1700
Data Index: 7592799 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.5068. Min Act: -0.1700
Data Index: 8165497 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.2880. Min Act: -0.1700
Data Index: 5539725 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.2255. Min Act: -0.1700
Data Index: 324644 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.1630. Min Act: -0.1700
Data Index: 6386483 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.1630. Min Act: -0.1700
Data Index: 659983 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.1318. Min Act: -0.1700
Data Index: 161034 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.0380. Min Act: -0.1700
Data Index: 3961921 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.0380. Min Act: -0.1700
Data Index: 3017898 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.0068. Min Act: -0.1700
Data Index: 6012121 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.0068. Min Act: -0.1700
Data Index: 2549174 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5380. Min Range: -7.5380
Max Act: 7.0068. Min Act: -0.1700
Data Index: 5578416 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.9755. Min Act: -0.1700
Data Index: 1084369 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.9755. Min Act: -0.1700
Data Index: 758168 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.9443. Min Act: -0.1700
Data Index: 644265 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.9130. Min Act: -0.1700
Data Index: 6134676 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.9130. Min Act: -0.1700
Data Index: 1498577 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.8818. Min Act: -0.1700
Data Index: 1663964 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.8818. Min Act: -0.1700
Data Index: 5318901 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5380. Min Range: -7.5380
Max Act: 6.8505. Min Act: -0.1700
Data Index: 4672024 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19