Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.2578. Min Act: -0.1700
Data Index: 8184099 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.2107. Min Act: -0.1700
Data Index: 477759 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.1949. Min Act: -0.1700
Data Index: 477758 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.1792. Min Act: -0.1700
Data Index: 5378300 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.1635. Min Act: -0.1700
Data Index: 3344501 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.1477. Min Act: -0.1700
Data Index: 5257293 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.1162. Min Act: -0.1700
Data Index: 1225144 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.1162. Min Act: -0.1700
Data Index: 1333239 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.1005. Min Act: -0.1700
Data Index: 5922121 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.0532. Min Act: -0.1700
Data Index: 6314610 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.0374. Min Act: -0.1700
Data Index: 3256964 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2578. Min Range: -3.2578
Max Act: 3.0058. Min Act: -0.1700
Data Index: 961273 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9900. Min Act: -0.1700
Data Index: 1435922 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9584. Min Act: -0.1700
Data Index: 3107137 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9742. Min Act: -0.1700
Data Index: 7537840 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9742. Min Act: -0.1700
Data Index: 1333241 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9584. Min Act: -0.1700
Data Index: 1800536 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9425. Min Act: -0.1700
Data Index: 1213165 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9584. Min Act: -0.1700
Data Index: 916108 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2578. Min Range: -3.2578
Max Act: 2.9425. Min Act: -0.1700
Data Index: 5105495 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19