Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5078 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.2015. Min Act: -0.1700
Data Index: 7530422 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.1078. Min Act: -0.1700
Data Index: 8273545 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.1078. Min Act: -0.1700
Data Index: 22312 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.0765. Min Act: -0.1700
Data Index: 5250312 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.0765. Min Act: -0.1700
Data Index: 3193004 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.0765. Min Act: -0.1700
Data Index: 2524748 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.0140. Min Act: -0.1700
Data Index: 8327949 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.0140. Min Act: -0.1700
Data Index: 5410891 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2015. Min Range: -6.2015
Max Act: 6.0140. Min Act: -0.1700
Data Index: 278438 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9828. Min Act: -0.1700
Data Index: 6387293 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9828. Min Act: -0.1700
Data Index: 4030976 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9828. Min Act: -0.1700
Data Index: 744267 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9828. Min Act: -0.1700
Data Index: 2692016 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9515. Min Act: -0.1700
Data Index: 5077680 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9515. Min Act: -0.1700
Data Index: 2673853 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9515. Min Act: -0.1700
Data Index: 1327143 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9828. Min Act: -0.1700
Data Index: 7323422 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9203. Min Act: -0.1700
Data Index: 2769269 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9203. Min Act: -0.1700
Data Index: 7310883 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2015. Min Range: -6.2015
Max Act: 5.9203. Min Act: -0.1700
Data Index: 2369899 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19