Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4919 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5501486 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.7342. Min Act: -0.1700
Data Index: 2076443 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5779. Min Act: -0.1700
Data Index: 8760620 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.6092. Min Act: -0.1700
Data Index: 1626968 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.6092. Min Act: -0.1700
Data Index: 3985073 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5779. Min Act: -0.1700
Data Index: 4678100 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5467. Min Act: -0.1700
Data Index: 7954908 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5779. Min Act: -0.1700
Data Index: 586325 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5467. Min Act: -0.1700
Data Index: 6077395 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5154. Min Act: -0.1700
Data Index: 3869429 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5154. Min Act: -0.1700
Data Index: 6087623 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.5154. Min Act: -0.1700
Data Index: 2376288 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.4842. Min Act: -0.1700
Data Index: 6716879 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.4842. Min Act: -0.1700
Data Index: 8154584 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.4529. Min Act: -0.1700
Data Index: 5654240 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.4529. Min Act: -0.1700
Data Index: 6472331 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.4217. Min Act: -0.1700
Data Index: 7030355 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.4217. Min Act: -0.1700
Data Index: 4063749 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.4217. Min Act: -0.1700
Data Index: 4487216 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7654. Min Range: -5.7654
Max Act: 5.3904. Min Act: -0.1700
Data Index: 5293946 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19