Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2506. Min Range: -9.2506
Max Act: 9.2506. Min Act: -0.1700
Data Index: 4574142 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.8131. Min Act: -0.1700
Data Index: 6363036 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.8131. Min Act: -0.1700
Data Index: 2317777 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.8131. Min Act: -0.1700
Data Index: 4965220 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.5006. Min Act: -0.1700
Data Index: 7298683 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.5006. Min Act: -0.1700
Data Index: 8177910 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.3756. Min Act: -0.1700
Data Index: 1364691 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.3756. Min Act: -0.1700
Data Index: 7435037 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 7792215 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 7758869 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 4808426 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 2116300 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 4605925 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 1881076 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 1615216 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 1945181 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 3584570 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 5919624 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 3175014 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2506. Min Range: -9.2506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 1114415 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19