Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.6980. Min Act: -0.1700
Data Index: 3579329 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.5730. Min Act: -0.1700
Data Index: 5611096 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.5418. Min Act: -0.1700
Data Index: 4553561 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.4793. Min Act: -0.1700
Data Index: 2077389 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.4480. Min Act: -0.1700
Data Index: 6143078 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.3543. Min Act: -0.1700
Data Index: 4914045 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.3543. Min Act: -0.1700
Data Index: 4964722 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.3543. Min Act: -0.1700
Data Index: 4626614 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.3230. Min Act: -0.1700
Data Index: 3319253 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.3230. Min Act: -0.1700
Data Index: 5541991 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.3230. Min Act: -0.1700
Data Index: 499358 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2918. Min Act: -0.1700
Data Index: 2739094 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2918. Min Act: -0.1700
Data Index: 4488157 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2605. Min Act: -0.1700
Data Index: 4301608 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2918. Min Act: -0.1700
Data Index: 7751165 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3078430 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2605. Min Act: -0.1700
Data Index: 6773155 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2605. Min Act: -0.1700
Data Index: 1440713 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2605. Min Act: -0.1700
Data Index: 7267418 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6980. Min Range: -6.6980
Max Act: 6.2605. Min Act: -0.1700
Data Index: 547205 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19