Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2337 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.7387. Min Act: -0.1700
Data Index: 7038419 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.7075. Min Act: -0.1700
Data Index: 4160866 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.6762. Min Act: -0.1700
Data Index: 5769805 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.6762. Min Act: -0.1700
Data Index: 8132695 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.6762. Min Act: -0.1700
Data Index: 6170052 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.6450. Min Act: -0.1700
Data Index: 1710356 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.6450. Min Act: -0.1700
Data Index: 1689451 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.6137. Min Act: -0.1700
Data Index: 579593 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.6137. Min Act: -0.1700
Data Index: 4763052 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.5512. Min Act: -0.1700
Data Index: 4280490 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.5512. Min Act: -0.1700
Data Index: 7407298 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.5512. Min Act: -0.1700
Data Index: 5609333 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.5200. Min Act: -0.1700
Data Index: 1846720 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.5200. Min Act: -0.1700
Data Index: 8122751 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.5200. Min Act: -0.1700
Data Index: 1429424 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.4887. Min Act: -0.1700
Data Index: 425735 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.4887. Min Act: -0.1700
Data Index: 2381617 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.4887. Min Act: -0.1700
Data Index: 436495 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.5200. Min Act: -0.1700
Data Index: 5295032 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7387. Min Range: -4.7387
Max Act: 4.4887. Min Act: -0.1700
Data Index: 4981312 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19