Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0697. Min Range: -5.0697
Max Act: 5.0697. Min Act: -0.1700
Data Index: 6462410 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0697. Min Range: -5.0697
Max Act: 5.0697. Min Act: -0.1700
Data Index: 5842683 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0697. Min Range: -5.0697
Max Act: 5.0697. Min Act: -0.1700
Data Index: 7116782 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0697. Min Range: -5.0697
Max Act: 5.0384. Min Act: -0.1700
Data Index: 5664143 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.9447. Min Act: -0.1700
Data Index: 5286681 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8822. Min Act: -0.1700
Data Index: 5026989 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.9134. Min Act: -0.1700
Data Index: 8345129 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8509. Min Act: -0.1700
Data Index: 2741530 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8822. Min Act: -0.1700
Data Index: 865069 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8822. Min Act: -0.1700
Data Index: 1215269 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8509. Min Act: -0.1700
Data Index: 7020475 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8509. Min Act: -0.1700
Data Index: 6877714 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8509. Min Act: -0.1700
Data Index: 1129582 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8509. Min Act: -0.1700
Data Index: 2348643 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8197. Min Act: -0.1700
Data Index: 6759838 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8509. Min Act: -0.1700
Data Index: 2833185 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.7884. Min Act: -0.1700
Data Index: 1360231 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8197. Min Act: -0.1700
Data Index: 779318 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.7884. Min Act: -0.1700
Data Index: 4043745 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0697. Min Range: -5.0697
Max Act: 4.8197. Min Act: -0.1700
Data Index: 120410 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19