Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0554. Min Range: -5.0554
Max Act: 5.0554. Min Act: -0.1700
Data Index: 6004304 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.9929. Min Act: -0.1700
Data Index: 679672 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.8991. Min Act: -0.1700
Data Index: 1950364 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.8054. Min Act: -0.1700
Data Index: 8562187 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.8366. Min Act: -0.1700
Data Index: 4807886 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.8679. Min Act: -0.1700
Data Index: 988712 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.7429. Min Act: -0.1700
Data Index: 8362318 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.7116. Min Act: -0.1700
Data Index: 7616989 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.7116. Min Act: -0.1700
Data Index: 5716731 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.7116. Min Act: -0.1700
Data Index: 6812259 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.7116. Min Act: -0.1700
Data Index: 5190854 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.7116. Min Act: -0.1700
Data Index: 4630531 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.6804. Min Act: -0.1700
Data Index: 3972526 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.6804. Min Act: -0.1700
Data Index: 2520119 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.6804. Min Act: -0.1700
Data Index: 1919188 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.6179. Min Act: -0.1700
Data Index: 81956 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.5866. Min Act: -0.1700
Data Index: 7975994 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.5866. Min Act: -0.1700
Data Index: 7910737 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.5866. Min Act: -0.1700
Data Index: 8201185 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0554. Min Range: -5.0554
Max Act: 4.5554. Min Act: -0.1700
Data Index: 6835926 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19