Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3432. Min Range: -9.3432
Max Act: 9.3432. Min Act: -0.1700
Data Index: 2366611 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3432. Min Range: -9.3432
Max Act: 9.1557. Min Act: -0.1700
Data Index: 3293569 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3432. Min Range: -9.3432
Max Act: 9.0932. Min Act: -0.1700
Data Index: 4619050 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3432. Min Range: -9.3432
Max Act: 9.0932. Min Act: -0.1700
Data Index: 7645700 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3432. Min Range: -9.3432
Max Act: 9.0932. Min Act: -0.1700
Data Index: 3348235 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.9682. Min Act: -0.1700
Data Index: 4937181 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.9682. Min Act: -0.1700
Data Index: 5095274 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.9057. Min Act: -0.1700
Data Index: 7235346 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.9057. Min Act: -0.1700
Data Index: 8103520 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.8432. Min Act: -0.1700
Data Index: 9007 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.8432. Min Act: -0.1700
Data Index: 2729719 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.9057. Min Act: -0.1700
Data Index: 8003452 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.9057. Min Act: -0.1700
Data Index: 4476119 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.7807. Min Act: -0.1700
Data Index: 977627 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.7807. Min Act: -0.1700
Data Index: 5332577 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.7807. Min Act: -0.1700
Data Index: 261972 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.7807. Min Act: -0.1700
Data Index: 7243001 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.7182. Min Act: -0.1700
Data Index: 4507800 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.6557. Min Act: -0.1700
Data Index: 880235 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3432. Min Range: -9.3432
Max Act: 8.6557. Min Act: -0.1700
Data Index: 982434 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19