Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2077. Min Range: -5.2077
Max Act: 5.2077. Min Act: -0.1700
Data Index: 8536960 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2077. Min Range: -5.2077
Max Act: 5.1140. Min Act: -0.1700
Data Index: 6995996 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2077. Min Range: -5.2077
Max Act: 5.0515. Min Act: -0.1700
Data Index: 3393904 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.9577. Min Act: -0.1700
Data Index: 2903864 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.9265. Min Act: -0.1700
Data Index: 6343704 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.8327. Min Act: -0.1700
Data Index: 2092292 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.8327. Min Act: -0.1700
Data Index: 4563287 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.8327. Min Act: -0.1700
Data Index: 6228849 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.8015. Min Act: -0.1700
Data Index: 5936405 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.7390. Min Act: -0.1700
Data Index: 8329017 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.7077. Min Act: -0.1700
Data Index: 1621924 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6765. Min Act: -0.1700
Data Index: 2682563 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6765. Min Act: -0.1700
Data Index: 7431359 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6765. Min Act: -0.1700
Data Index: 7047362 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6765. Min Act: -0.1700
Data Index: 5020074 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6765. Min Act: -0.1700
Data Index: 7071263 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6452. Min Act: -0.1700
Data Index: 8427209 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6140. Min Act: -0.1700
Data Index: 8486178 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6452. Min Act: -0.1700
Data Index: 7282968 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2077. Min Range: -5.2077
Max Act: 4.6452. Min Act: -0.1700
Data Index: 8054515 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19