Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2251. Min Range: -7.2251
Max Act: 7.2251. Min Act: -0.1700
Data Index: 3645118 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2251. Min Range: -7.2251
Max Act: 7.0063. Min Act: -0.1700
Data Index: 282298 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.8188. Min Act: -0.1700
Data Index: 4396325 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.7563. Min Act: -0.1700
Data Index: 6354555 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.6938. Min Act: -0.1700
Data Index: 8266216 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.6313. Min Act: -0.1700
Data Index: 1069223 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.6001. Min Act: -0.1700
Data Index: 1958121 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.6001. Min Act: -0.1700
Data Index: 7260753 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.5688. Min Act: -0.1700
Data Index: 4790036 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.5376. Min Act: -0.1700
Data Index: 7589461 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.5376. Min Act: -0.1700
Data Index: 822959 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.5376. Min Act: -0.1700
Data Index: 2374206 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.5688. Min Act: -0.1700
Data Index: 3714590 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.5063. Min Act: -0.1700
Data Index: 4542366 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.4751. Min Act: -0.1700
Data Index: 6474841 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.5063. Min Act: -0.1700
Data Index: 6107476 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.4438. Min Act: -0.1700
Data Index: 7147658 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.4126. Min Act: -0.1700
Data Index: 5797887 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.4126. Min Act: -0.1700
Data Index: 3841961 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2251. Min Range: -7.2251
Max Act: 6.3813. Min Act: -0.1700
Data Index: 3472525 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19