Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5007 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.8969. Min Act: -0.1700
Data Index: 495038 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.7094. Min Act: -0.1700
Data Index: 3102551 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.6469. Min Act: -0.1700
Data Index: 3474586 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5844. Min Act: -0.1700
Data Index: 6966026 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.6469. Min Act: -0.1700
Data Index: 4493266 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.6469. Min Act: -0.1700
Data Index: 8081371 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5844. Min Act: -0.1700
Data Index: 6682694 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5532. Min Act: -0.1700
Data Index: 4751565 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5532. Min Act: -0.1700
Data Index: 5357937 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5532. Min Act: -0.1700
Data Index: 7074285 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5532. Min Act: -0.1700
Data Index: 6273525 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4907. Min Act: -0.1700
Data Index: 5369342 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5219. Min Act: -0.1700
Data Index: 4226028 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4907. Min Act: -0.1700
Data Index: 3278604 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4594. Min Act: -0.1700
Data Index: 7580397 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4594. Min Act: -0.1700
Data Index: 514978 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4282. Min Act: -0.1700
Data Index: 6114237 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4282. Min Act: -0.1700
Data Index: 601843 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.3969. Min Act: -0.1700
Data Index: 1308871 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.3969. Min Act: -0.1700
Data Index: 5721217 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19