Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.8136. Min Act: -0.1700
Data Index: 3056557 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.7823. Min Act: -0.1700
Data Index: 6947625 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.6261. Min Act: -0.1700
Data Index: 4855359 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.3761. Min Act: -0.1700
Data Index: 4145136 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.3448. Min Act: -0.1700
Data Index: 2797223 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.3448. Min Act: -0.1700
Data Index: 4889812 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.2511. Min Act: -0.1700
Data Index: 2826155 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.2198. Min Act: -0.1700
Data Index: 3549693 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.2198. Min Act: -0.1700
Data Index: 2405440 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.1886. Min Act: -0.1700
Data Index: 8714416 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.1886. Min Act: -0.1700
Data Index: 8142214 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.1573. Min Act: -0.1700
Data Index: 2814920 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.1261. Min Act: -0.1700
Data Index: 5982361 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.0948. Min Act: -0.1700
Data Index: 7522911 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.0948. Min Act: -0.1700
Data Index: 5964807 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.1261. Min Act: -0.1700
Data Index: 7176110 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.1261. Min Act: -0.1700
Data Index: 6950578 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.0948. Min Act: -0.1700
Data Index: 7574808 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.0948. Min Act: -0.1700
Data Index: 7687966 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8136. Min Range: -7.8136
Max Act: 7.0948. Min Act: -0.1700
Data Index: 7786760 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19