Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4005 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.5792. Min Act: -0.1700
Data Index: 1052231 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.3917. Min Act: -0.1700
Data Index: 6141558 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2980. Min Act: -0.1700
Data Index: 3354600 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2980. Min Act: -0.1700
Data Index: 3967239 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2667. Min Act: -0.1700
Data Index: 1255359 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2980. Min Act: -0.1700
Data Index: 2352897 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2355. Min Act: -0.1700
Data Index: 8052255 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2355. Min Act: -0.1700
Data Index: 2440764 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2355. Min Act: -0.1700
Data Index: 7935498 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2355. Min Act: -0.1700
Data Index: 2927914 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.2042. Min Act: -0.1700
Data Index: 3612359 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.1105. Min Act: -0.1700
Data Index: 8504244 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.1105. Min Act: -0.1700
Data Index: 2876559 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.1105. Min Act: -0.1700
Data Index: 3740319 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.0792. Min Act: -0.1700
Data Index: 8228076 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.0792. Min Act: -0.1700
Data Index: 4502050 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.0480. Min Act: -0.1700
Data Index: 6603422 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.0480. Min Act: -0.1700
Data Index: 7071324 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.0480. Min Act: -0.1700
Data Index: 869562 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5792. Min Range: -7.5792
Max Act: 7.0480. Min Act: -0.1700
Data Index: 3026404 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19