Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.3205. Min Act: -0.1700
Data Index: 1371884 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.2893. Min Act: -0.1700
Data Index: 8122025 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.2580. Min Act: -0.1700
Data Index: 117376 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.1330. Min Act: -0.1700
Data Index: 575219 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.1330. Min Act: -0.1700
Data Index: 6792747 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0705. Min Act: -0.1700
Data Index: 7227861 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.1018. Min Act: -0.1700
Data Index: 2247053 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0392. Min Act: -0.1700
Data Index: 7364963 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0392. Min Act: -0.1700
Data Index: 74202 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0080. Min Act: -0.1700
Data Index: 1191311 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0392. Min Act: -0.1700
Data Index: 2849767 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9923. Min Act: -0.1700
Data Index: 3393758 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0080. Min Act: -0.1700
Data Index: 7861296 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0080. Min Act: -0.1700
Data Index: 6625519 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9923. Min Act: -0.1700
Data Index: 6630750 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9923. Min Act: -0.1700
Data Index: 4069704 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9923. Min Act: -0.1700
Data Index: 3218904 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9455. Min Act: -0.1700
Data Index: 6803163 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9611. Min Act: -0.1700
Data Index: 3068371 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9611. Min Act: -0.1700
Data Index: 7069688 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19