Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5040. Min Range: -8.5040
Max Act: 8.5040. Min Act: -0.1700
Data Index: 8127210 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5040. Min Range: -8.5040
Max Act: 8.3165. Min Act: -0.1700
Data Index: 8583403 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5040. Min Range: -8.5040
Max Act: 8.1290. Min Act: -0.1700
Data Index: 3210297 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5040. Min Range: -8.5040
Max Act: 8.0665. Min Act: -0.1700
Data Index: 5963365 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5040. Min Range: -8.5040
Max Act: 8.0040. Min Act: -0.1700
Data Index: 8356234 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5040. Min Range: -8.5040
Max Act: 8.0040. Min Act: -0.1700
Data Index: 7470248 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.8790. Min Act: -0.1700
Data Index: 6159969 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.8790. Min Act: -0.1700
Data Index: 7414265 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.8165. Min Act: -0.1700
Data Index: 2953793 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.8165. Min Act: -0.1700
Data Index: 7882897 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.8165. Min Act: -0.1700
Data Index: 1071672 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.7540. Min Act: -0.1700
Data Index: 3894871 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.7540. Min Act: -0.1700
Data Index: 6984262 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.8165. Min Act: -0.1700
Data Index: 5058808 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.6915. Min Act: -0.1700
Data Index: 4989605 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.6915. Min Act: -0.1700
Data Index: 8067452 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.6915. Min Act: -0.1700
Data Index: 7125490 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.6915. Min Act: -0.1700
Data Index: 275703 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.6290. Min Act: -0.1700
Data Index: 4529080 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5040. Min Range: -8.5040
Max Act: 7.6290. Min Act: -0.1700
Data Index: 2314213 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19