Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2186 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.8252. Min Act: -0.1700
Data Index: 7031830 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.8252. Min Act: -0.1700
Data Index: 7306859 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.8252. Min Act: -0.1700
Data Index: 7539546 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.7940. Min Act: -0.1700
Data Index: 57412 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6776673 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.6690. Min Act: -0.1700
Data Index: 7720539 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.6065. Min Act: -0.1700
Data Index: 5267730 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.6065. Min Act: -0.1700
Data Index: 877384 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5440. Min Act: -0.1700
Data Index: 1092462 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5440. Min Act: -0.1700
Data Index: 1945803 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5440. Min Act: -0.1700
Data Index: 5656852 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5440. Min Act: -0.1700
Data Index: 8769362 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5127. Min Act: -0.1700
Data Index: 8268797 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5752. Min Act: -0.1700
Data Index: 2940992 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5127. Min Act: -0.1700
Data Index: 3759625 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5127. Min Act: -0.1700
Data Index: 7000550 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.5127. Min Act: -0.1700
Data Index: 7590781 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.4815. Min Act: -0.1700
Data Index: 4132698 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.4502. Min Act: -0.1700
Data Index: 1300756 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8252. Min Range: -4.8252
Max Act: 4.4502. Min Act: -0.1700
Data Index: 2539195 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19