Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2300 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.8012. Min Act: -0.1700
Data Index: 7930682 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.5199. Min Act: -0.1700
Data Index: 3707445 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.4887. Min Act: -0.1700
Data Index: 3260545 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.4574. Min Act: -0.1700
Data Index: 6671731 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.4262. Min Act: -0.1700
Data Index: 8207112 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3949. Min Act: -0.1700
Data Index: 2497911 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3949. Min Act: -0.1700
Data Index: 2392262 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3949. Min Act: -0.1700
Data Index: 4132128 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.4262. Min Act: -0.1700
Data Index: 4480662 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3949. Min Act: -0.1700
Data Index: 6149748 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3949. Min Act: -0.1700
Data Index: 3532912 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3949. Min Act: -0.1700
Data Index: 4750182 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3637. Min Act: -0.1700
Data Index: 2064400 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3637. Min Act: -0.1700
Data Index: 4088196 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3637. Min Act: -0.1700
Data Index: 7684989 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3637. Min Act: -0.1700
Data Index: 3687668 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3324. Min Act: -0.1700
Data Index: 1655389 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3324. Min Act: -0.1700
Data Index: 5344207 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3324. Min Act: -0.1700
Data Index: 1796353 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8012. Min Range: -6.8012
Max Act: 6.3637. Min Act: -0.1700
Data Index: 7815382 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19