Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.5216. Min Act: -0.1700
Data Index: 1955132 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.4278. Min Act: -0.1700
Data Index: 2580764 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3966. Min Act: -0.1700
Data Index: 469247 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3653. Min Act: -0.1700
Data Index: 2283240 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3653. Min Act: -0.1700
Data Index: 6445911 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3341. Min Act: -0.1700
Data Index: 6238732 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3341. Min Act: -0.1700
Data Index: 1446679 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3341. Min Act: -0.1700
Data Index: 7078850 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3028. Min Act: -0.1700
Data Index: 339417 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2716. Min Act: -0.1700
Data Index: 3790179 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2403. Min Act: -0.1700
Data Index: 4114353 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2716. Min Act: -0.1700
Data Index: 6259005 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2716. Min Act: -0.1700
Data Index: 2004924 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2716. Min Act: -0.1700
Data Index: 8135554 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2091. Min Act: -0.1700
Data Index: 2972478 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2091. Min Act: -0.1700
Data Index: 2329074 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2091. Min Act: -0.1700
Data Index: 1024116 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.1778. Min Act: -0.1700
Data Index: 367182 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2091. Min Act: -0.1700
Data Index: 5661416 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.1778. Min Act: -0.1700
Data Index: 7542641 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19