Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1055 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1929. Min Range: -6.1929
Max Act: 6.1929. Min Act: -0.1700
Data Index: 3091092 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.9116. Min Act: -0.1700
Data Index: 8706091 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.8491. Min Act: -0.1699
Data Index: 975568 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.8491. Min Act: -0.1700
Data Index: 315274 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.8491. Min Act: -0.1700
Data Index: 7260520 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.8179. Min Act: -0.1700
Data Index: 170596 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.7554. Min Act: -0.1700
Data Index: 6679994 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.7241. Min Act: -0.1700
Data Index: 2990631 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.7241. Min Act: -0.1699
Data Index: 5606911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.7241. Min Act: -0.1698
Data Index: 2549576 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.6929. Min Act: -0.1700
Data Index: 5210258 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.6929. Min Act: -0.1700
Data Index: 3559971 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.6616. Min Act: -0.1700
Data Index: 8530908 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.6616. Min Act: -0.1700
Data Index: 1810621 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.6304. Min Act: -0.1700
Data Index: 6663164 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.5991. Min Act: -0.1700
Data Index: 3415072 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.6304. Min Act: -0.1698
Data Index: 1069279 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.5991. Min Act: -0.1700
Data Index: 2630423 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.5991. Min Act: -0.1700
Data Index: 6186298 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1929. Min Range: -6.1929
Max Act: 5.5991. Min Act: -0.1700
Data Index: 6280675 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19