Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1687 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.5185. Min Act: -0.1700
Data Index: 5815367 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.3310. Min Act: -0.1700
Data Index: 8637388 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.2372. Min Act: -0.1700
Data Index: 7694139 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.2372. Min Act: -0.1700
Data Index: 8816028 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.2060. Min Act: -0.1700
Data Index: 3886417 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.2060. Min Act: -0.1700
Data Index: 5167090 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.2060. Min Act: -0.1700
Data Index: 1831876 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.2060. Min Act: -0.1700
Data Index: 2213427 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.1435. Min Act: -0.1700
Data Index: 841567 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.1435. Min Act: -0.1700
Data Index: 6672649 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.1122. Min Act: -0.1700
Data Index: 3190697 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.0810. Min Act: -0.1700
Data Index: 579498 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.1435. Min Act: -0.1700
Data Index: 1247904 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.0810. Min Act: -0.1700
Data Index: 6395909 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.0497. Min Act: -0.1700
Data Index: 2706764 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.0185. Min Act: -0.1700
Data Index: 2213598 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5185. Min Range: -7.5185
Max Act: 7.0185. Min Act: -0.1700
Data Index: 972694 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5185. Min Range: -7.5185
Max Act: 6.9872. Min Act: -0.1700
Data Index: 5410559 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5185. Min Range: -7.5185
Max Act: 6.9247. Min Act: -0.1700
Data Index: 4479840 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5185. Min Range: -7.5185
Max Act: 6.9560. Min Act: -0.1700
Data Index: 3036000 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19