Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6162 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2237. Min Range: -7.2237
Max Act: 7.2237. Min Act: -0.1700
Data Index: 6658191 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.8487. Min Act: -0.1700
Data Index: 1196497 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.6925. Min Act: -0.1700
Data Index: 414990 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.6612. Min Act: -0.1700
Data Index: 7119946 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5987. Min Act: -0.1700
Data Index: 8444456 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5987. Min Act: -0.1700
Data Index: 8048975 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5362. Min Act: -0.1700
Data Index: 5591540 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5362. Min Act: -0.1700
Data Index: 7429182 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5362. Min Act: -0.1700
Data Index: 6185032 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5362. Min Act: -0.1700
Data Index: 5000979 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5050. Min Act: -0.1700
Data Index: 5286442 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.5362. Min Act: -0.1700
Data Index: 2124854 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4737. Min Act: -0.1700
Data Index: 6551503 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4737. Min Act: -0.1700
Data Index: 455073 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4737. Min Act: -0.1700
Data Index: 2420732 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4737. Min Act: -0.1700
Data Index: 8435277 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4737. Min Act: -0.1700
Data Index: 116426 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4425. Min Act: -0.1700
Data Index: 5515961 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4425. Min Act: -0.1700
Data Index: 5496366 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2237. Min Range: -7.2237
Max Act: 6.4425. Min Act: -0.1700
Data Index: 6685866 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19