Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.6650. Min Act: -0.1700
Data Index: 2075766 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.5400. Min Act: -0.1700
Data Index: 4120701 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.5088. Min Act: -0.1700
Data Index: 818103 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.4775. Min Act: -0.1700
Data Index: 901091 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.4463. Min Act: -0.1700
Data Index: 7532290 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.4463. Min Act: -0.1700
Data Index: 1075352 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.3525. Min Act: -0.1700
Data Index: 3522331 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.3213. Min Act: -0.1700
Data Index: 4930950 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.2275. Min Act: -0.1700
Data Index: 711224 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.2275. Min Act: -0.1700
Data Index: 5448938 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.2275. Min Act: -0.1700
Data Index: 4818784 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1650. Min Act: -0.1700
Data Index: 7745051 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1650. Min Act: -0.1700
Data Index: 5309767 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1650. Min Act: -0.1700
Data Index: 263650 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1338. Min Act: -0.1700
Data Index: 3715415 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1338. Min Act: -0.1700
Data Index: 711223 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1025. Min Act: -0.1700
Data Index: 176918 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1025. Min Act: -0.1700
Data Index: 8358875 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.1025. Min Act: -0.1700
Data Index: 5139189 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6650. Min Range: -5.6650
Max Act: 5.0713. Min Act: -0.1700
Data Index: 4473454 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19