Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4675 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0532. Min Range: -10.0532
Max Act: 10.0532. Min Act: -0.1700
Data Index: 4267164 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.4907. Min Act: -0.1700
Data Index: 1106394 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.1782. Min Act: -0.1700
Data Index: 3321568 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.1782. Min Act: -0.1700
Data Index: 6797743 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.1157. Min Act: -0.1700
Data Index: 538894 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.1157. Min Act: -0.1700
Data Index: 5640834 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.0532. Min Act: -0.1700
Data Index: 3014851 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.0532. Min Act: -0.1700
Data Index: 8085256 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.0532. Min Act: -0.1700
Data Index: 6215801 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.0532. Min Act: -0.1700
Data Index: 2127023 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0532. Min Range: -10.0532
Max Act: 9.0532. Min Act: -0.1700
Data Index: 3543405 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.9282. Min Act: -0.1700
Data Index: 2896037 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.9282. Min Act: -0.1700
Data Index: 6432164 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.9282. Min Act: -0.1700
Data Index: 380746 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.9282. Min Act: -0.1700
Data Index: 3026144 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.9282. Min Act: -0.1700
Data Index: 1356752 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.9282. Min Act: -0.1700
Data Index: 7756484 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.9907. Min Act: -0.1700
Data Index: 7755555 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.8657. Min Act: -0.1700
Data Index: 7139628 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0532. Min Range: -10.0532
Max Act: 8.8657. Min Act: -0.1700
Data Index: 7251838 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19