Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0747. Min Range: -6.0747
Max Act: 6.0747. Min Act: -0.1700
Data Index: 5753342 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.8872. Min Act: -0.1700
Data Index: 2286178 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.8559. Min Act: -0.1700
Data Index: 5389056 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.7934. Min Act: -0.1700
Data Index: 4868245 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.7309. Min Act: -0.1700
Data Index: 2435225 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.6997. Min Act: -0.1700
Data Index: 1273919 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.6684. Min Act: -0.1700
Data Index: 3956141 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.5747. Min Act: -0.1700
Data Index: 6810590 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.5122. Min Act: -0.1700
Data Index: 4416936 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.4809. Min Act: -0.1700
Data Index: 5182001 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.4497. Min Act: -0.1700
Data Index: 1253870 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.4184. Min Act: -0.1700
Data Index: 6337629 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.4497. Min Act: -0.1700
Data Index: 5925604 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.4497. Min Act: -0.1700
Data Index: 6296755 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.4184. Min Act: -0.1700
Data Index: 6618101 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.3872. Min Act: -0.1700
Data Index: 8086071 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.3559. Min Act: -0.1700
Data Index: 4897505 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.3559. Min Act: -0.1700
Data Index: 7078167 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.3872. Min Act: -0.1700
Data Index: 6619185 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0747. Min Range: -6.0747
Max Act: 5.3559. Min Act: -0.1700
Data Index: 803826 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19