Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4218 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.9778. Min Act: -0.1700
Data Index: 6230130 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.9778. Min Act: -0.1700
Data Index: 516460 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.9465. Min Act: -0.1700
Data Index: 856980 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.9465. Min Act: -0.1700
Data Index: 975469 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.9465. Min Act: -0.1700
Data Index: 6447168 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7903. Min Act: -0.1700
Data Index: 6810228 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7903. Min Act: -0.1700
Data Index: 505359 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7590. Min Act: -0.1700
Data Index: 4457297 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7590. Min Act: -0.1700
Data Index: 688084 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7590. Min Act: -0.1700
Data Index: 5249473 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7278. Min Act: -0.1700
Data Index: 4540365 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7590. Min Act: -0.1700
Data Index: 5683703 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7590. Min Act: -0.1700
Data Index: 2006152 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.7278. Min Act: -0.1700
Data Index: 2721422 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.6965. Min Act: -0.1700
Data Index: 7166693 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.6965. Min Act: -0.1700
Data Index: 2475627 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.6965. Min Act: -0.1700
Data Index: 4015066 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.6653. Min Act: -0.1700
Data Index: 2108345 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.6340. Min Act: -0.1700
Data Index: 4389853 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9778. Min Range: -5.9778
Max Act: 5.6340. Min Act: -0.1700
Data Index: 1382190 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19