Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.3833. Min Act: -0.1700
Data Index: 4844235 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.4146. Min Act: -0.1700
Data Index: 7462578 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.3833. Min Act: -0.1700
Data Index: 223280 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.3521. Min Act: -0.1700
Data Index: 2567808 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2896. Min Act: -0.1700
Data Index: 3907030 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.3208. Min Act: -0.1700
Data Index: 374161 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.3208. Min Act: -0.1700
Data Index: 4345255 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2896. Min Act: -0.1700
Data Index: 5473038 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2896. Min Act: -0.1700
Data Index: 3375734 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2896. Min Act: -0.1700
Data Index: 3927744 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2896. Min Act: -0.1700
Data Index: 8401673 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2583. Min Act: -0.1700
Data Index: 3639530 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2583. Min Act: -0.1700
Data Index: 2027400 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2271. Min Act: -0.1700
Data Index: 4306276 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2271. Min Act: -0.1700
Data Index: 8394556 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2583. Min Act: -0.1700
Data Index: 3071831 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2271. Min Act: -0.1700
Data Index: 6879375 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2583. Min Act: -0.1700
Data Index: 1568896 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2583. Min Act: -0.1700
Data Index: 2665636 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4146. Min Range: -5.4146
Max Act: 5.2583. Min Act: -0.1700
Data Index: 264716 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19