Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.2163. Min Act: -0.1700
Data Index: 6573124 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.1850. Min Act: -0.1700
Data Index: 4523180 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.1225. Min Act: -0.1700
Data Index: 7641552 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0913. Min Act: -0.1700
Data Index: 4222439 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0913. Min Act: -0.1700
Data Index: 2531418 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0600. Min Act: -0.1700
Data Index: 8007591 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0600. Min Act: -0.1700
Data Index: 4414952 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 2257446 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 123333 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 1366984 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 6011732 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 3705671 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 8317383 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 1239460 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 5823774 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 4976460 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 257821 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9350. Min Act: -0.1700
Data Index: 4092412 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9038. Min Act: -0.1700
Data Index: 6236703 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9350. Min Act: -0.1700
Data Index: 351705 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19