Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0222. Min Range: -9.0222
Max Act: 9.0222. Min Act: -0.1700
Data Index: 4835099 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.8972. Min Act: -0.1700
Data Index: 7249012 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.8347. Min Act: -0.1700
Data Index: 7340517 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.8347. Min Act: -0.1700
Data Index: 471782 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7722. Min Act: -0.1700
Data Index: 4806741 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7722. Min Act: -0.1700
Data Index: 4301115 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7722. Min Act: -0.1700
Data Index: 7005703 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7097. Min Act: -0.1700
Data Index: 163295 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7722. Min Act: -0.1700
Data Index: 1661177 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 4187437 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7097. Min Act: -0.1700
Data Index: 818354 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7097. Min Act: -0.1700
Data Index: 2849868 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 1698477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.7097. Min Act: -0.1700
Data Index: 1875533 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 3459305 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 6390813 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 5189646 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 518618 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 1894815 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0222. Min Range: -9.0222
Max Act: 8.6472. Min Act: -0.1700
Data Index: 79807 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19