Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 418 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.5369. Min Act: -0.1699
Data Index: 6983534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.4432. Min Act: -0.1700
Data Index: 5714781 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.4432. Min Act: -0.1700
Data Index: 2868119 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.4432. Min Act: -0.1700
Data Index: 2523528 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.4432. Min Act: -0.1700
Data Index: 7510719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.2557. Min Act: -0.1700
Data Index: 2096956 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.2244. Min Act: -0.1700
Data Index: 1315911 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.1619. Min Act: -0.1700
Data Index: 7808410 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.1619. Min Act: -0.1700
Data Index: 196579 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.1932. Min Act: -0.1699
Data Index: 1854174 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.1306. Min Act: -0.1700
Data Index: 7333925 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0994. Min Act: -0.1700
Data Index: 7313169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0994. Min Act: -0.1700
Data Index: 3257177 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0994. Min Act: -0.1700
Data Index: 2506055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0994. Min Act: -0.1700
Data Index: 6554238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0681. Min Act: -0.1700
Data Index: 3886002 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0994. Min Act: -0.1700
Data Index: 2590011 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0994. Min Act: -0.1700
Data Index: 710622 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0369. Min Act: -0.1700
Data Index: 4418025 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5369. Min Range: -4.5369
Max Act: 4.0681. Min Act: -0.1700
Data Index: 5685116 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19