Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.3609. Min Act: -0.1700
Data Index: 2370046 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.3295. Min Act: -0.1700
Data Index: 7633224 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2981. Min Act: -0.1700
Data Index: 7154856 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2824. Min Act: -0.1700
Data Index: 1349353 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2824. Min Act: -0.1700
Data Index: 8076567 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2981. Min Act: -0.1700
Data Index: 2404175 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2824. Min Act: -0.1700
Data Index: 8051670 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2824. Min Act: -0.1700
Data Index: 2540607 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2667. Min Act: -0.1700
Data Index: 7105610 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2510. Min Act: -0.1700
Data Index: 5886909 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2196. Min Act: -0.1700
Data Index: 5573588 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2353. Min Act: -0.1700
Data Index: 4078499 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2353. Min Act: -0.1700
Data Index: 2404164 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2196. Min Act: -0.1700
Data Index: 154110 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2353. Min Act: -0.1700
Data Index: 2166477 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2039. Min Act: -0.1700
Data Index: 3609180 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2039. Min Act: -0.1700
Data Index: 2225470 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2039. Min Act: -0.1700
Data Index: 5206923 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.2039. Min Act: -0.1700
Data Index: 7398583 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3609. Min Range: -3.3609
Max Act: 3.1724. Min Act: -0.1700
Data Index: 2060637 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19