Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4921 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9670. Min Act: -0.1700
Data Index: 2246027 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9670. Min Act: -0.1700
Data Index: 3474189 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9357. Min Act: -0.1700
Data Index: 3747880 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9357. Min Act: -0.1700
Data Index: 686109 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9357. Min Act: -0.1700
Data Index: 8662746 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9045. Min Act: -0.1700
Data Index: 2246030 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9045. Min Act: -0.1700
Data Index: 7329252 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.9045. Min Act: -0.1700
Data Index: 2214002 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8732. Min Act: -0.1700
Data Index: 984559 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8732. Min Act: -0.1700
Data Index: 2246028 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8732. Min Act: -0.1700
Data Index: 5390445 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8420. Min Act: -0.1700
Data Index: 2246031 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.7795. Min Act: -0.1699
Data Index: 3689542 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8107. Min Act: -0.1700
Data Index: 8023512 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.7795. Min Act: -0.1700
Data Index: 4278548 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8107. Min Act: -0.1700
Data Index: 6955269 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8107. Min Act: -0.1700
Data Index: 6787515 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8107. Min Act: -0.1700
Data Index: 5451900 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.8107. Min Act: -0.1700
Data Index: 3217485 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9670. Min Range: -4.9670
Max Act: 4.7795. Min Act: -0.1700
Data Index: 4848258 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19