Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1512. Min Range: -5.1512
Max Act: 5.1512. Min Act: -0.1700
Data Index: 4165885 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1512. Min Range: -5.1512
Max Act: 5.1200. Min Act: -0.1700
Data Index: 8004274 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1512. Min Range: -5.1512
Max Act: 5.0887. Min Act: -0.1700
Data Index: 3341811 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1512. Min Range: -5.1512
Max Act: 5.0887. Min Act: -0.1700
Data Index: 4196327 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1512. Min Range: -5.1512
Max Act: 5.0262. Min Act: -0.1700
Data Index: 3341801 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9950. Min Act: -0.1700
Data Index: 3094231 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9950. Min Act: -0.1700
Data Index: 730077 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9950. Min Act: -0.1700
Data Index: 3695103 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9950. Min Act: -0.1700
Data Index: 2821013 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9950. Min Act: -0.1700
Data Index: 7141042 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9950. Min Act: -0.1700
Data Index: 3341796 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9325. Min Act: -0.1700
Data Index: 8032586 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9637. Min Act: -0.1700
Data Index: 8721897 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9637. Min Act: -0.1700
Data Index: 2378120 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9637. Min Act: -0.1700
Data Index: 5266625 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9637. Min Act: -0.1700
Data Index: 3157523 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9637. Min Act: -0.1700
Data Index: 6359326 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9325. Min Act: -0.1700
Data Index: 866785 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9325. Min Act: -0.1700
Data Index: 1822572 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1512. Min Range: -5.1512
Max Act: 4.9325. Min Act: -0.1700
Data Index: 4949386 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19