Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.5601. Min Act: -0.1700
Data Index: 3385577 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.5288. Min Act: -0.1700
Data Index: 1149705 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.4976. Min Act: -0.1698
Data Index: 3186696 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.4663. Min Act: -0.1700
Data Index: 5067281 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.4038. Min Act: -0.1700
Data Index: 1423174 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.4038. Min Act: -0.1700
Data Index: 2000670 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3726. Min Act: -0.1700
Data Index: 3496805 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3726. Min Act: -0.1700
Data Index: 4872418 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3101. Min Act: -0.1700
Data Index: 8084239 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3413. Min Act: -0.1700
Data Index: 8553137 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3101. Min Act: -0.1700
Data Index: 387188 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3101. Min Act: -0.1700
Data Index: 1972304 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3101. Min Act: -0.1700
Data Index: 4353752 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3101. Min Act: -0.1700
Data Index: 4242271 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.3101. Min Act: -0.1700
Data Index: 567516 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.2788. Min Act: -0.1700
Data Index: 4917471 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.2788. Min Act: -0.1700
Data Index: 4805141 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.2788. Min Act: -0.1700
Data Index: 1972303 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.2788. Min Act: -0.1700
Data Index: 4238064 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5601. Min Range: -5.5601
Max Act: 5.2788. Min Act: -0.1700
Data Index: 5602106 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19