Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4153 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2067. Min Range: -5.2067
Max Act: 5.2067. Min Act: -0.1700
Data Index: 6578168 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2067. Min Range: -5.2067
Max Act: 5.1130. Min Act: -0.1700
Data Index: 5931825 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2067. Min Range: -5.2067
Max Act: 5.0192. Min Act: -0.1700
Data Index: 1419232 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.9880. Min Act: -0.1700
Data Index: 8030377 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.9255. Min Act: -0.1700
Data Index: 6813363 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.8317. Min Act: -0.1700
Data Index: 4545645 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.7692. Min Act: -0.1700
Data Index: 919089 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.7067. Min Act: -0.1700
Data Index: 7624535 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.7380. Min Act: -0.1700
Data Index: 8627444 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6755. Min Act: -0.1700
Data Index: 7871891 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6755. Min Act: -0.1700
Data Index: 466775 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6442. Min Act: -0.1700
Data Index: 428959 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6755. Min Act: -0.1700
Data Index: 7112714 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6442. Min Act: -0.1700
Data Index: 4493388 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6442. Min Act: -0.1700
Data Index: 5555935 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6442. Min Act: -0.1700
Data Index: 4292034 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.6130. Min Act: -0.1700
Data Index: 113894 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.5817. Min Act: -0.1700
Data Index: 5013462 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.5817. Min Act: -0.1700
Data Index: 3666102 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2067. Min Range: -5.2067
Max Act: 4.5817. Min Act: -0.1700
Data Index: 3710706 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19