Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1479 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3591. Min Range: -8.3591
Max Act: 8.3591. Min Act: -0.1700
Data Index: 5899219 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3591. Min Range: -8.3591
Max Act: 8.1716. Min Act: -0.1700
Data Index: 2356317 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.9841. Min Act: -0.1700
Data Index: 2999599 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.9216. Min Act: -0.1700
Data Index: 4272804 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.8279. Min Act: -0.1700
Data Index: 3311002 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.7029. Min Act: -0.1700
Data Index: 2804664 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.6091. Min Act: -0.1700
Data Index: 8786513 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.5779. Min Act: -0.1700
Data Index: 1723763 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.5779. Min Act: -0.1700
Data Index: 8304187 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.5779. Min Act: -0.1700
Data Index: 6530199 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.5466. Min Act: -0.1700
Data Index: 7237277 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.5154. Min Act: -0.1700
Data Index: 997 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.4841. Min Act: -0.1700
Data Index: 1169766 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.4216. Min Act: -0.1700
Data Index: 8174472 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.4529. Min Act: -0.1700
Data Index: 2550139 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.4216. Min Act: -0.1700
Data Index: 7412200 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.3591. Min Act: -0.1700
Data Index: 1962714 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.3591. Min Act: -0.1700
Data Index: 5386714 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.3591. Min Act: -0.1700
Data Index: 7618048 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3591. Min Range: -8.3591
Max Act: 7.3279. Min Act: -0.1700
Data Index: 3252016 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19