Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2309 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.7831. Min Act: -0.1700
Data Index: 7000103 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.7831. Min Act: -0.1700
Data Index: 3031022 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.7206. Min Act: -0.1700
Data Index: 5224805 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.6581. Min Act: -0.1700
Data Index: 6970607 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.6581. Min Act: -0.1700
Data Index: 2534511 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5956. Min Act: -0.1700
Data Index: 891038 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5956. Min Act: -0.1700
Data Index: 5167671 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5956. Min Act: -0.1700
Data Index: 8645261 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5956. Min Act: -0.1700
Data Index: 5558522 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5956. Min Act: -0.1700
Data Index: 1109624 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5956. Min Act: -0.1700
Data Index: 4464542 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5331. Min Act: -0.1700
Data Index: 8435591 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5331. Min Act: -0.1700
Data Index: 6471909 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.5331. Min Act: -0.1700
Data Index: 1859172 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.4706. Min Act: -0.1700
Data Index: 2036719 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.4706. Min Act: -0.1700
Data Index: 8059220 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.3456. Min Act: -0.1700
Data Index: 3332284 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.4081. Min Act: -0.1700
Data Index: 4125588 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.4081. Min Act: -0.1700
Data Index: 7106218 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7831. Min Range: -9.7831
Max Act: 9.3456. Min Act: -0.1700
Data Index: 775703 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19