Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0201. Min Range: -4.0201
Max Act: 4.0201. Min Act: -0.1700
Data Index: 3069802 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9889. Min Act: -0.1700
Data Index: 2513789 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9889. Min Act: -0.1700
Data Index: 6224596 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9576. Min Act: -0.1700
Data Index: 8198673 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9576. Min Act: -0.1700
Data Index: 3069805 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8638. Min Act: -0.1700
Data Index: 2349210 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8326. Min Act: -0.1700
Data Index: 8198662 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8326. Min Act: -0.1700
Data Index: 3069803 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8326. Min Act: -0.1700
Data Index: 3069804 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8326. Min Act: -0.1700
Data Index: 4730624 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8326. Min Act: -0.1700
Data Index: 3069809 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8013. Min Act: -0.1700
Data Index: 4866798 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8013. Min Act: -0.1700
Data Index: 5319001 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8013. Min Act: -0.1700
Data Index: 8143685 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8013. Min Act: -0.1700
Data Index: 6283841 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.7700. Min Act: -0.1700
Data Index: 3501441 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.7700. Min Act: -0.1700
Data Index: 765641 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.7700. Min Act: -0.1700
Data Index: 2710322 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.7700. Min Act: -0.1700
Data Index: 5690663 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.7700. Min Act: -0.1700
Data Index: 7248565 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19