Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1559 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.7235. Min Act: -0.1700
Data Index: 531039 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.7547. Min Act: -0.1700
Data Index: 4722525 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.6922. Min Act: -0.1700
Data Index: 2217540 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.6922. Min Act: -0.1700
Data Index: 6339662 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5985. Min Act: -0.1700
Data Index: 4116646 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5985. Min Act: -0.1700
Data Index: 4427389 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5985. Min Act: -0.1700
Data Index: 4735676 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5985. Min Act: -0.1700
Data Index: 1280902 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5360. Min Act: -0.1700
Data Index: 7544530 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5672. Min Act: -0.1700
Data Index: 3595576 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5672. Min Act: -0.1700
Data Index: 4970305 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5360. Min Act: -0.1700
Data Index: 4414662 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5360. Min Act: -0.1700
Data Index: 2661212 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5360. Min Act: -0.1700
Data Index: 2271240 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5360. Min Act: -0.1700
Data Index: 6951575 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5360. Min Act: -0.1700
Data Index: 3763653 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5047. Min Act: -0.1700
Data Index: 4414664 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5047. Min Act: -0.1700
Data Index: 839721 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5047. Min Act: -0.1700
Data Index: 603277 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7547. Min Range: -4.7547
Max Act: 4.5047. Min Act: -0.1700
Data Index: 1128216 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19