Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0356. Min Range: -9.0356
Max Act: 9.0356. Min Act: -0.1700
Data Index: 7882592 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.9106. Min Act: -0.1700
Data Index: 3992297 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.7856. Min Act: -0.1700
Data Index: 739448 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.7856. Min Act: -0.1700
Data Index: 211421 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.7231. Min Act: -0.1700
Data Index: 7738580 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.7231. Min Act: -0.1700
Data Index: 7594454 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.6606. Min Act: -0.1700
Data Index: 4760284 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.6606. Min Act: -0.1700
Data Index: 2017589 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.6606. Min Act: -0.1700
Data Index: 1228211 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.6606. Min Act: -0.1700
Data Index: 3199638 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.5981. Min Act: -0.1700
Data Index: 650184 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.5981. Min Act: -0.1700
Data Index: 335622 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.5356. Min Act: -0.1700
Data Index: 1625731 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.5356. Min Act: -0.1700
Data Index: 4232724 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.5356. Min Act: -0.1700
Data Index: 8091731 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.5356. Min Act: -0.1700
Data Index: 1248296 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.4731. Min Act: -0.1700
Data Index: 3160751 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.4731. Min Act: -0.1700
Data Index: 821362 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.4731. Min Act: -0.1700
Data Index: 3684901 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0356. Min Range: -9.0356
Max Act: 8.4106. Min Act: -0.1700
Data Index: 1954278 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19