Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2071 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.6440. Min Act: -0.1700
Data Index: 37705 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.5502. Min Act: -0.1700
Data Index: 2284544 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.5502. Min Act: -0.1700
Data Index: 98622 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.4877. Min Act: -0.1700
Data Index: 7321304 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.4877. Min Act: -0.1700
Data Index: 3967003 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.4877. Min Act: -0.1700
Data Index: 5931037 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3627. Min Act: -0.1700
Data Index: 8321201 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3627. Min Act: -0.1700
Data Index: 2041992 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3627. Min Act: -0.1700
Data Index: 4648469 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 8078602 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 1261772 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3315. Min Act: -0.1700
Data Index: 4408838 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 5256019 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 1107964 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 901327 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 6612073 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 68437 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 862124 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.3002. Min Act: -0.1700
Data Index: 3244050 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6440. Min Range: -5.6440
Max Act: 5.2690. Min Act: -0.1700
Data Index: 549095 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19