Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4739 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6205. Min Range: -9.6205
Max Act: 9.6205. Min Act: -0.1700
Data Index: 1697188 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.8705. Min Act: -0.1700
Data Index: 701084 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.8080. Min Act: -0.1700
Data Index: 3277157 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.7455. Min Act: -0.1700
Data Index: 1376274 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.5580. Min Act: -0.1700
Data Index: 7380914 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.4955. Min Act: -0.1700
Data Index: 7085387 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.5268. Min Act: -0.1700
Data Index: 1380256 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.3705. Min Act: -0.1700
Data Index: 8048546 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.3080. Min Act: -0.1700
Data Index: 5499882 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.2455. Min Act: -0.1700
Data Index: 860913 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.2143. Min Act: -0.1700
Data Index: 2063391 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.1830. Min Act: -0.1700
Data Index: 8779219 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.1830. Min Act: -0.1700
Data Index: 6947855 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.1830. Min Act: -0.1700
Data Index: 6743950 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.1518. Min Act: -0.1700
Data Index: 8366151 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.1205. Min Act: -0.1700
Data Index: 2847332 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.0893. Min Act: -0.1700
Data Index: 1504701 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6205. Min Range: -9.6205
Max Act: 8.0268. Min Act: -0.1700
Data Index: 1744024 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6205. Min Range: -9.6205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 4819875 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6205. Min Range: -9.6205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 4830226 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19