Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 180 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0918. Min Range: -7.0918
Max Act: 7.0918. Min Act: -0.1700
Data Index: 1076963 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.9356. Min Act: -0.1697
Data Index: 873328 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.9356. Min Act: -0.1700
Data Index: 1954113 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.9043. Min Act: -0.1700
Data Index: 7493931 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.9043. Min Act: -0.1700
Data Index: 3791447 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.9043. Min Act: -0.1700
Data Index: 2310323 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8731. Min Act: -0.1700
Data Index: 7784828 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8418. Min Act: -0.1700
Data Index: 1954111 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8418. Min Act: -0.1700
Data Index: 6781554 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8418. Min Act: -0.1700
Data Index: 7784837 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8418. Min Act: -0.1700
Data Index: 1913501 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8418. Min Act: -0.1700
Data Index: 7600725 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8106. Min Act: -0.1700
Data Index: 1954112 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8106. Min Act: -0.1700
Data Index: 7784826 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.8106. Min Act: -0.1700
Data Index: 7525844 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.7481. Min Act: -0.1700
Data Index: 8514586 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.7481. Min Act: -0.1700
Data Index: 4433701 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.7168. Min Act: -0.1700
Data Index: 2942899 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.7168. Min Act: -0.1700
Data Index: 1852168 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0918. Min Range: -7.0918
Max Act: 6.7168. Min Act: -0.1700
Data Index: 6512693 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19