Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1424. Min Range: -5.1424
Max Act: 5.1424. Min Act: -0.1700
Data Index: 8206842 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1424. Min Range: -5.1424
Max Act: 5.1112. Min Act: -0.1700
Data Index: 6646424 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1424. Min Range: -5.1424
Max Act: 5.1112. Min Act: -0.1700
Data Index: 8730972 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1424. Min Range: -5.1424
Max Act: 5.0174. Min Act: -0.1700
Data Index: 1173963 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8924. Min Act: -0.1700
Data Index: 4996566 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.9549. Min Act: -0.1700
Data Index: 1277852 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8924. Min Act: -0.1700
Data Index: 8700364 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8924. Min Act: -0.1700
Data Index: 7087880 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8612. Min Act: -0.1700
Data Index: 162717 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8924. Min Act: -0.1700
Data Index: 5045929 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8612. Min Act: -0.1700
Data Index: 1594145 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8924. Min Act: -0.1700
Data Index: 5536001 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8612. Min Act: -0.1700
Data Index: 2469253 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8299. Min Act: -0.1700
Data Index: 5598112 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8612. Min Act: -0.1700
Data Index: 2770608 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8299. Min Act: -0.1700
Data Index: 48395 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.8299. Min Act: -0.1700
Data Index: 3160642 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.7987. Min Act: -0.1700
Data Index: 7600148 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.7987. Min Act: -0.1700
Data Index: 5006222 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1424. Min Range: -5.1424
Max Act: 4.7987. Min Act: -0.1700
Data Index: 318316 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19