Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5605 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2001. Min Range: -5.2001
Max Act: 5.2001. Min Act: -0.1700
Data Index: 8194970 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.9188. Min Act: -0.1700
Data Index: 5115091 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.8563. Min Act: -0.1700
Data Index: 1130255 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.8876. Min Act: -0.1700
Data Index: 4428750 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.8876. Min Act: -0.1700
Data Index: 6041239 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.8876. Min Act: -0.1700
Data Index: 1702182 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.8251. Min Act: -0.1700
Data Index: 5765158 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.8251. Min Act: -0.1700
Data Index: 1310916 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.8251. Min Act: -0.1700
Data Index: 7448569 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7938. Min Act: -0.1700
Data Index: 1508747 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7313. Min Act: -0.1700
Data Index: 1302300 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7626. Min Act: -0.1700
Data Index: 3020800 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7313. Min Act: -0.1700
Data Index: 7101156 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7313. Min Act: -0.1700
Data Index: 2836539 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7001. Min Act: -0.1700
Data Index: 265933 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7001. Min Act: -0.1700
Data Index: 952241 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7001. Min Act: -0.1700
Data Index: 3212919 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.7001. Min Act: -0.1700
Data Index: 7456861 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.6688. Min Act: -0.1700
Data Index: 4402493 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2001. Min Range: -5.2001
Max Act: 4.6376. Min Act: -0.1700
Data Index: 7316315 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19