Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1797 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.6690. Min Act: -0.1700
Data Index: 8275726 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.6065. Min Act: -0.1700
Data Index: 3059049 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.6065. Min Act: -0.1700
Data Index: 6516014 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.5440. Min Act: -0.1700
Data Index: 11547 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.5127. Min Act: -0.1700
Data Index: 4404375 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4815. Min Act: -0.1700
Data Index: 946628 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.5127. Min Act: -0.1700
Data Index: 8275725 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4815. Min Act: -0.1700
Data Index: 3059050 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4815. Min Act: -0.1700
Data Index: 7767222 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4815. Min Act: -0.1700
Data Index: 4542161 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4815. Min Act: -0.1700
Data Index: 5741875 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4502. Min Act: -0.1700
Data Index: 3732250 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4502. Min Act: -0.1700
Data Index: 6516013 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4815. Min Act: -0.1700
Data Index: 4763477 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4502. Min Act: -0.1700
Data Index: 1577967 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4190. Min Act: -0.1700
Data Index: 8337065 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4502. Min Act: -0.1700
Data Index: 1711630 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4190. Min Act: -0.1700
Data Index: 3389269 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3877. Min Act: -0.1700
Data Index: 3556441 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3877. Min Act: -0.1700
Data Index: 2688247 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19